Axis Iliad - Codebase Intelligence For Agentic Commerce

Official36 tools

by lastmanupinc-hub · TypeScript

Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.

io.github.lastmanupinc-hub/axis-toolbox MCP Server

This MCP server provides codebase intelligence for agents by exposing structured artifacts derived from a codebase. It is documented under the canonical name “Axis' Iliad” and is associated with 152 structured artifacts across 21 programs, with one call to retrieve them. The repository is tracked with tests and coverage badges.

🛠️ Key Features

Codebase intelligence for agents
Produces 152 structured artifacts across 21 programs
One-call delivery of the structured artifacts
Canonical name: “Axis' Iliad”

🚀 Use Cases

Supplying agents with “agent-ready” canonical workspace artifacts
Turning raw codebases into consistent, structured outputs across multiple programs

⚡ Developer Benefits

Predictable structure: 21 programs and 152 artifacts in a single call
Tooling surface indicated by toolCount: 36

⚠️ Limitations

The server context describes a single call pattern; details beyond artifact generation are not provided.

Captured live from the server via tools/list.

analyze_repo

Analyze a GitHub repository and generate 141 structured AXIS artifacts across 20 programs. Returns snapshot_id plus an artifacts listing; use get_artifact to read files and get_snapshot to re-enumerate outputs without re-running analysis. Requires Authorization: Bearer <api_key>. Use this when the source of truth is a GitHub repo URL. Pricing: $0.50 standard, $0.15 lite budget mode, $25 engineer per repo. Engineer mode (X-Agent-Mode: engineer — Living Architecture) adds a verified LLM specificity pass: a living-architecture.md whose every architectural claim is grounded in the repo's extracted facts or dropped. This is the paid path for full repo analysis and can return authentication, quota, payment-required, invalid-URL, or GitHub-fetch errors. private repos require a stored GitHub token. Use analyze_files instead for inline file payloads or list_programs/search_and_discover_tools when you are still selecting a workflow.

Parameters1

github_url

string

required

GitHub repository URL (https://github.com/owner/repo)

Raw schema

{
  "type": "object",
  "properties": {
    "github_url": {
      "type": "string",
      "description": "GitHub repository URL (https://github.com/owner/repo)"
    }
  },
  "required": [
    "github_url"
  ]
}

analyze_files

Analyze source files directly and generate the full 141-artifact AXIS bundle without using GitHub. Returns snapshot_id plus artifact listing; use this for local, generated, or unsaved code. Requires Authorization: Bearer <api_key>. Use analyze_repo for GitHub URLs or improve_my_agent_with_axis for recommendation-first agent hardening.

Parameters5

project_name	string	required	Name of the project
project_type	string	required	Project type (web_application, api_service, cli_tool, library, monorepo)
frameworks	array	required	Detected or known frameworks
goals	array	required	Analysis goals
files	array	required	Source files to analyze

Raw schema

{
  "type": "object",
  "properties": {
    "project_name": {
      "type": "string",
      "description": "Name of the project"
    },
    "project_type": {
      "type": "string",
      "description": "Project type (web_application, api_service, cli_tool, library, monorepo)"
    },
    "frameworks": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Detected or known frameworks"
    },
    "goals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Analysis goals"
    },
    "files": {
      "type": "array",
      "description": "Source files to analyze",
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "File path relative to project root"
          },
          "content": {
            "type": "string",
            "description": "File content (UTF-8)"
          }
        }
      }
    }
  },
  "required": [
    "project_name",
    "project_type",
    "frameworks",
    "goals",
    "files"
  ]
}

list_programs

Inventory mode. List all 20 AXIS programs, their generators, pricing tier, and artifact paths. Free, no auth, and no side effects. Use search_and_discover_tools instead when you only have a keyword, or discover_commerce_tools when you need install and onboarding metadata.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_snapshot

Retrieve status and the full artifact listing for a prior analysis by snapshot_id. Use this to re-enumerate artifact paths without re-running analysis. Snapshots persist and can be shared between agents to avoid duplicate analysis costs.

Parameters1

snapshot_id

string

required

Snapshot ID returned by analyze_repo or analyze_files

Raw schema

{
  "type": "object",
  "properties": {
    "snapshot_id": {
      "type": "string",
      "description": "Snapshot ID returned by analyze_repo or analyze_files"
    }
  },
  "required": [
    "snapshot_id"
  ]
}

get_artifact

Read one generated artifact by snapshot_id and path. Requires access to the snapshot and may return snapshot-not-found, invalid-path, or artifact-not-found errors. Example: snapshot_id=abc-123, path=AGENTS.md. Use this when you need the full text of one artifact. Use get_snapshot instead when you first need the artifact list.

Parameters2

snapshot_id	string	required	Snapshot ID
path	string	required	Artifact file path as returned in the artifacts list

Raw schema

{
  "type": "object",
  "properties": {
    "snapshot_id": {
      "type": "string",
      "description": "Snapshot ID"
    },
    "path": {
      "type": "string",
      "description": "Artifact file path as returned in the artifacts list"
    }
  },
  "required": [
    "snapshot_id",
    "path"
  ]
}

prepare_agentic_purchasing_preview

Compute a free Purchasing Readiness Score (0-100) and gap list for a codebase without generating artifacts. No auth, no charge, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. Returns score, risk_level, top gaps, frameworks detected, and which AXIS programs would close which gaps. Use this to triage 'should I pay for the full hardening bundle?' before calling prepare_agentic_purchasing. The paid version generates the full artifact bundle including CE 3.0 dispute evidence, SCA exemption matrix, and TAP interop.

Parameters4

project_name	string	required	Name of the project being previewed
project_type	string	optional	Optional project type hint (web_application, api_service, cli_tool, library, monorepo)
frameworks	array	optional	Optional framework hints
files	array	required	Source files to triage (max 25 files, 50KB each, 1MB total)

Raw schema

{
  "type": "object",
  "properties": {
    "project_name": {
      "type": "string",
      "description": "Name of the project being previewed"
    },
    "project_type": {
      "type": "string",
      "description": "Optional project type hint (web_application, api_service, cli_tool, library, monorepo)"
    },
    "frameworks": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional framework hints"
    },
    "files": {
      "type": "array",
      "description": "Source files to triage (max 25 files, 50KB each, 1MB total)",
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string"
          },
          "content": {
            "type": "string"
          }
        }
      }
    }
  },
  "required": [
    "project_name",
    "files"
  ]
}

prepare_agentic_purchasing

Prepare a codebase for agentic purchasing and return a readiness score plus commerce artifacts. Requires Authorization: Bearer <api_key>; paid analysis records a new snapshot and may return auth, quota, payment, file-limit, or validation errors. Example: submit checkout files with focus_areas=["sca","dispute"]. Use this when you need AP2/UCP/Visa, CE 3.0 dispute evidence, checkout, dispute, and negotiation hardening. Engineer mode (X-Agent-Mode: engineer — Commerce Integration, $250): also emits a deployable x402/AP2/PAI'D endpoint + a runnable sandbox test + a schema-validatable CE 3.0 pack + a transparent dispute-readiness score (a working integration, not just a score), plus a deployable Stripe network-token read adapter when a stripe signal is detected. Use discover_agentic_purchasing_needs instead when you only need workflow triage.

Parameters11

project_name	string	required	Name of the project
project_type	string	required	Project type (web_application, api_service, cli_tool, library, monorepo)
frameworks	array	required	Detected or known frameworks
goals	array	required	Project goals
files	array	required	Array of {path, content} objects representing source files
focus	string	optional	Analysis focus (default: purchasing)
agent_type	string	optional	Consuming agent type hint
focus_areas	array	optional	Compliance focus areas
budget_per_run_cents	number	optional	Agent budget for this call in cents
spending_window	string	optional	Agent spending window
referral_token	string	optional	Optional referral token from another agent

Raw schema

{
  "type": "object",
  "properties": {
    "project_name": {
      "type": "string",
      "description": "Name of the project"
    },
    "project_type": {
      "type": "string",
      "description": "Project type (web_application, api_service, cli_tool, library, monorepo)"
    },
    "frameworks": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Detected or known frameworks"
    },
    "goals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Project goals"
    },
    "files": {
      "type": "array",
      "description": "Array of {path, content} objects representing source files",
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string"
          },
          "content": {
            "type": "string"
          }
        }
      }
    },
    "focus": {
      "type": "string",
      "enum": [
        "full",
        "purchasing",
        "security",
        "optimization"
      ],
      "description": "Analysis focus (default: purchasing)"
    },
    "agent_type": {
      "type": "string",
      "description": "Consuming agent type hint"
    },
    "focus_areas": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "sca",
          "dispute",
          "mandate",
          "tap",
          "tokenization"
        ]
      },
      "description": "Compliance focus areas"
    },
    "budget_per_run_cents": {
      "type": "number",
      "description": "Agent budget for this call in cents"
    },
    "spending_window": {
      "type": "string",
      "enum": [
        "per_call",
        "hourly",
        "daily",
        "monthly"
      ],
      "description": "Agent spending window"
    },
    "referral_token": {
      "type": "string",
      "description": "Optional referral token from another agent"
    }
  },
  "required": [
    "project_name",
    "project_type",
    "frameworks",
    "goals",
    "files"
  ]
}

closer

Take a 70-80% complete project directory and generate complete professional packaging + marketplace certification artifacts so it is ready to ship and sell.

Parameters5

snapshot_id	string	optional	Existing AXIS snapshot_id to package into a distributable product
project_root	string	optional	Optional local project root path hint (metadata only in remote MCP mode)
product_name	string	optional	Optional branding override for product name
tagline	string	optional	Optional branding tagline
target_marketplaces	array	optional	Optional marketplaces list (e.g. npm, unreal, vscode, dockerhub, github-marketplace)

Raw schema

{
  "type": "object",
  "properties": {
    "snapshot_id": {
      "type": "string",
      "description": "Existing AXIS snapshot_id to package into a distributable product"
    },
    "project_root": {
      "type": "string",
      "description": "Optional local project root path hint (metadata only in remote MCP mode)"
    },
    "product_name": {
      "type": "string",
      "description": "Optional branding override for product name"
    },
    "tagline": {
      "type": "string",
      "description": "Optional branding tagline"
    },
    "target_marketplaces": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional marketplaces list (e.g. npm, unreal, vscode, dockerhub, github-marketplace)"
    }
  }
}

deploy

Generate a zero-pipeline-minutes deploy bundle: stack-aware Dockerfile, .dockerignore, dev compose, render.yaml (Render existing-image), wrangler.pages.toml + wrangler.containers.toml + worker.ts (Cloudflare), bash/PowerShell push scripts, and a qualification report. The project builds locally in VSCode, pushes images to GHCR or via wrangler, and Render/Cloudflare just pulls — no GitHub Actions minutes, no Render build pipeline minutes, no CF build minutes.

Parameters1

snapshot_id

string

required

Existing AXIS snapshot_id to package into deploy artifacts

Raw schema

{
  "type": "object",
  "properties": {
    "snapshot_id": {
      "type": "string",
      "description": "Existing AXIS snapshot_id to package into deploy artifacts"
    }
  },
  "required": [
    "snapshot_id"
  ]
}

search_and_discover_tools

Search AXIS programs by keyword and return ranked matches with artifact paths. Free, no auth, and no stateful side effects. Example: q=checkout returns commerce-relevant programs first. Use this when you know the outcome you want but not the right program. Use list_programs instead for the full catalog, discover_commerce_tools for install metadata, or discover_agentic_purchasing_needs for purchasing-specific triage.

Parameters2

q	string	optional	Search query â€” keyword or phrase
program	string	optional	Optional: filter results to a specific program name

Raw schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Search query â€” keyword or phrase"
    },
    "program": {
      "type": "string",
      "description": "Optional: filter results to a specific program name"
    }
  }
}

discover_commerce_tools

Discover AXIS install metadata, pricing, and shareable manifests for commerce-capable agents. Free, no auth, and no mutation beyond read access. Example: call before wiring AXIS into Claude Desktop, Cursor, or VS Code. Use this when you need onboarding and ecosystem setup details. Use search_and_discover_tools instead for keyword routing or discover_agentic_purchasing_needs for purchasing-task triage.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

improve_my_agent_with_axis

Analyze an agent codebase and return a prioritized AXIS hardening plan. Requires Authorization: Bearer <api_key>; this creates a snapshot and may return auth, quota, file-limit, or validation errors. Example: pass your agent source files to see missing AGENTS.md, CLAUDE.md, and MCP config gaps. Use this when you want recommendations and missing-context detection. Use analyze_files instead when you want the full artifact bundle directly.

Parameters2

project_name	string	required	Name of the agent/project to improve
files	array	required	Source files of the agent to analyze

Raw schema

{
  "type": "object",
  "properties": {
    "project_name": {
      "type": "string",
      "description": "Name of the agent/project to improve"
    },
    "files": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "File path relative to project root"
          },
          "content": {
            "type": "string",
            "description": "File content (UTF-8)"
          }
        }
      },
      "description": "Source files of the agent to analyze"
    }
  },
  "required": [
    "project_name",
    "files"
  ]
}

discover_agentic_purchasing_needs

Discover the best AXIS workflow for a purchasing or compliance task. Free, no auth, and logs lightweight task metadata for intent analytics. Example: task_description='prepare for autonomous Visa checkout'. Use this when you need commerce-specific triage and next-step guidance. Use search_and_discover_tools instead for non-commerce keyword routing across all programs.

Parameters3

task_description	string	optional	What the agent is trying to accomplish
current_readiness	number	optional	Optional: current Purchasing Readiness Score (0-100) if known
focus_areas	array	optional	Optional: specific areas to focus on

Raw schema

{
  "type": "object",
  "properties": {
    "task_description": {
      "type": "string",
      "description": "What the agent is trying to accomplish"
    },
    "current_readiness": {
      "type": "number",
      "description": "Optional: current Purchasing Readiness Score (0-100) if known"
    },
    "focus_areas": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional: specific areas to focus on"
    }
  }
}

get_referral_code

Get or create the caller's AXIS referral token. Requires Authorization: Bearer <api_key>, has no usage charge, and may persist a new referral code if one does not exist yet. Example: call before sharing AXIS with another agent or workspace. Use this when you need the shareable token itself. Use get_referral_credits instead when you need balances, milestones, and discount status.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_referral_credits

Get the caller's referral earnings, milestones, and free-call status. Requires Authorization: Bearer <api_key>, has no usage charge, and returns the current discount ledger without creating a new analysis. Example: call after a referral campaign to inspect earned credits. Use this when you need balances and milestones. Use get_referral_code instead when you only need the shareable token.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

iliad_web_research

Scrape a single URL with AXIS's owned crawler (SSRF-guarded fetch, robots.txt-aware, readability extraction — no third-party key) and return markdown-formatted content. Honest scope: fetches static HTML only, no JavaScript rendering, so client-rendered SPA pages may extract thin content. Returns markdown body, extracted metadata, and title. Best for research, documentation reading, or SEO analysis. Requires Authorization: Bearer <api_key>. Pricing: $0.10 standard, $0.05 lite per page. Use iliad_web_research_crawl for crawling multiple pages or link following.

Parameters2

url	string	required	The URL to scrape (http or https)
only_main_content	boolean	optional	Extract only the main content (default: true)

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to scrape (http or https)"
    },
    "only_main_content": {
      "type": "boolean",
      "description": "Extract only the main content (default: true)",
      "default": true
    }
  },
  "required": [
    "url"
  ]
}

iliad_web_research_crawl

Crawl a domain with AXIS's owned crawler — a same-origin BFS frontier with robots.txt compliance and per-host politeness, no third-party key — and scrape multiple pages. Honest scope: static HTML only, no JavaScript rendering. Returns array of scraped pages with markdown content. Best for site mapping, content audits, or bulk research. Requires Authorization: Bearer <api_key>. Pricing: $0.25 standard, $0.12 lite per page crawled (up to 100 pages per request). Use iliad_web_research for single-page scrapes.

Parameters2

url	string	required	The domain/URL to crawl (http or https)
limit	number	optional	Maximum pages to crawl (1-100, default: 10)

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The domain/URL to crawl (http or https)"
    },
    "limit": {
      "type": "number",
      "description": "Maximum pages to crawl (1-100, default: 10)",
      "minimum": 1,
      "maximum": 100,
      "default": 10
    }
  },
  "required": [
    "url"
  ]
}

iliad_object_storage

AXIS-owned signed-URL minter backed by Cloudflare R2. Returns a pre-signed PUT or GET URL scoped to the calling account (keys are prefixed with `accounts/<account_id>/` server-side, so accounts can't reach each other's objects). Requires Authorization: Bearer <api_key>. Returns the URL plus expires_at (ISO 8601), bucket, and scoped_key. Returns `{_not_configured: true, ...}` when the operator has not provisioned R2_* env vars (no crash, no leaked secrets). TTL is capped at 86400 seconds (24h). Engineer mode (X-Agent-Mode: engineer — Managed Bucket, $0.05): adds delete + list + copy (server-side, no bytes through the agent) operations, content-addressed dedup keys (content_sha256), and mint-time PUT policy (pin content_type / exact content_length as signed headers R2 enforces).

Parameters8

key	string	required	Object key (max 1024 chars), or the prefix for operation=list. Path traversal and leading-/ are rejected.
operation	string	required	put / get (standard). delete / list / copy and content-addressed put require X-Agent-Mode: engineer (Managed Bucket).
content_sha256	string	optional	Engineer mode: 64-char hex sha256 of the bytes you'll PUT. When set, the object lands under accounts/<id>/cas/<sha256> so identical content dedupes.
ext	string	optional	Engineer mode: optional extension appended to the content-addressed key (e.g. 'png').
source_key	string	optional	Engineer mode (operation=copy): source object key to copy from, scoped to your account; `key` is the destination. Echo the returned required_headers on the PUT.
content_type	string	optional	Engineer mode (put): pin the Content-Type the upload must send (signed; R2 rejects a mismatch). Printable ASCII type/subtype, ≤255 chars. Echo via required_headers.
content_length	number	optional	Engineer mode (put): pin the EXACT byte size the upload must be (signed; ≤5 GiB). Pairs with content_sha256 for verified content-addressed writes.
ttl_seconds	number	optional	Signed-URL lifetime, 1..86400. Defaults to 3600.

Raw schema

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string",
      "description": "Object key (max 1024 chars), or the prefix for operation=list. Path traversal and leading-/ are rejected."
    },
    "operation": {
      "type": "string",
      "description": "put / get (standard). delete / list / copy and content-addressed put require X-Agent-Mode: engineer (Managed Bucket).",
      "enum": [
        "put",
        "get",
        "delete",
        "list",
        "copy"
      ]
    },
    "content_sha256": {
      "type": "string",
      "description": "Engineer mode: 64-char hex sha256 of the bytes you'll PUT. When set, the object lands under accounts/<id>/cas/<sha256> so identical content dedupes."
    },
    "ext": {
      "type": "string",
      "description": "Engineer mode: optional extension appended to the content-addressed key (e.g. 'png')."
    },
    "source_key": {
      "type": "string",
      "description": "Engineer mode (operation=copy): source object key to copy from, scoped to your account; `key` is the destination. Echo the returned required_headers on the PUT."
    },
    "content_type": {
      "type": "string",
      "description": "Engineer mode (put): pin the Content-Type the upload must send (signed; R2 rejects a mismatch). Printable ASCII type/subtype, ≤255 chars. Echo via required_headers."
    },
    "content_length": {
      "type": "number",
      "description": "Engineer mode (put): pin the EXACT byte size the upload must be (signed; ≤5 GiB). Pairs with content_sha256 for verified content-addressed writes."
    },
    "ttl_seconds": {
      "type": "number",
      "description": "Signed-URL lifetime, 1..86400. Defaults to 3600."
    }
  },
  "required": [
    "key",
    "operation"
  ]
}

iliad_vector_database

AXIS-owned vector store. Two operations: `upsert` (insert or replace vectors) and `query` (cosine top-k nearest neighbors). Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`), so tenants cannot read each other's vectors. Persistent across restarts via Postgres. Requires Authorization: Bearer <api_key>. Best for RAG retrievers, deduplication, and similarity search. Engineer mode (X-Agent-Mode: engineer — Managed Memory, $0.05): query runs a pgvector/HNSW ANN candidate pool with optional recency-decay reranking (recency_half_life_days — managed forgetting), RRF hybrid fusion (sparse_ids), and metadata filter; upsert applies intra-batch semantic-dedup (dedup_threshold).

Parameters6

operation	string	required	upsert (insert/replace) or query (top-k cosine).
namespace	string	optional	Logical isolation key. Defaults to 'default'. Account ID is always prepended server-side.
vectors	array	optional	Array of {id, vector, metadata?} — required for upsert.
query	object	optional	{vector: number[], top_k?: number, filter?: object}. Engineer mode also reads recency_half_life_days (number — exponential recency decay) and sparse_ids (string[] — RRF hybrid fusion). Required for query.
dedup_threshold	number	optional	Engineer upsert: cosine threshold for intra-batch semantic-dedup (default 0.97).
semantic_dedup	boolean	optional	Engineer upsert: set false to disable dedup (default on).

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "description": "upsert (insert/replace) or query (top-k cosine).",
      "enum": [
        "upsert",
        "query"
      ]
    },
    "namespace": {
      "type": "string",
      "description": "Logical isolation key. Defaults to 'default'. Account ID is always prepended server-side."
    },
    "vectors": {
      "type": "array",
      "description": "Array of {id, vector, metadata?} — required for upsert."
    },
    "query": {
      "type": "object",
      "description": "{vector: number[], top_k?: number, filter?: object}. Engineer mode also reads recency_half_life_days (number — exponential recency decay) and sparse_ids (string[] — RRF hybrid fusion). Required for query."
    },
    "dedup_threshold": {
      "type": "number",
      "description": "Engineer upsert: cosine threshold for intra-batch semantic-dedup (default 0.97)."
    },
    "semantic_dedup": {
      "type": "boolean",
      "description": "Engineer upsert: set false to disable dedup (default on)."
    }
  },
  "required": [
    "operation"
  ]
}

iliad_embeddings

Convert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input. AXIS-owned in-process inference by default (node-llama-cpp + an embedding-capable GGUF at AXIS_EMBEDDING_MODEL_PATH — no upstream provider call); an optional OpenAI /v1/embeddings backend is available behind AXIS_EMBEDDING_BACKEND=openai (model: text-embedding-3-small by default, overridable via OPENAI_EMBEDDING_MODEL; reports token usage). Requires Authorization: Bearer <api_key> to call. When the selected backend is not provisioned (local: GGUF file absent; openai: OPENAI_API_KEY unset), returns a structured `_not_configured: true` envelope naming the backend and remediation. Pairs natively with iliad_vector_database — feed `vectors` from this tool's output into `vector` of the vector_database upsert/query calls. Engineer mode (X-Agent-Mode: engineer — Domain Embeddings, $0.08): pass `dimensions` (Matryoshka truncation → smaller vectors) and/or `corpus_adapter: true` (mean-center the batch to sharpen retrieval on your data); returns an `engineer` block with the fitted adapter_mean for query alignment.

Parameters3

input	string \| array	required	A single string or an array of strings to embed. Empty strings and entries > 32k chars are rejected (chunk before calling).
dimensions	number	optional	Engineer mode: truncate each vector to this many leading dims (Matryoshka) + renormalize. Smaller, cheaper vectors.
corpus_adapter	boolean	optional	Engineer mode: mean-center the batch (all-but-the-mean) to sharpen retrieval; returns the fitted adapter_mean.

Raw schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": [
        "string",
        "array"
      ],
      "description": "A single string or an array of strings to embed. Empty strings and entries > 32k chars are rejected (chunk before calling)."
    },
    "dimensions": {
      "type": "number",
      "description": "Engineer mode: truncate each vector to this many leading dims (Matryoshka) + renormalize. Smaller, cheaper vectors."
    },
    "corpus_adapter": {
      "type": "boolean",
      "description": "Engineer mode: mean-center the batch (all-but-the-mean) to sharpen retrieval; returns the fitted adapter_mean."
    }
  },
  "required": [
    "input"
  ]
}

iliad_transactional_email

Send a single transactional email. Requires Authorization: Bearer <api_key>. Provide either body_html, body_text, or both (Resend will pick the best variant per recipient). All emails ship from RESEND_FROM_ADDRESS — operator must verify that domain in Resend before sending. Returns the provider-assigned message_id plus the accepted recipient list. Returns a structured _not_configured envelope when RESEND_API_KEY or RESEND_FROM_ADDRESS is missing. Recipients capped at 50 per call; subject capped at 998 chars; bodies capped at 1 MB. Engineer mode (X-Agent-Mode: engineer — Deliverability, $0.50): instead of sending, pass a `domain` and get a full SPF/DKIM/DMARC setup (fresh DKIM keypair) + sender warmup schedule + verification checklist — no email sent, no ESP key needed.

Parameters9

to	string \| array	optional	Recipient address or array of addresses (max 50). Required for a send (standard mode).
domain	string	optional	Engineer mode (Deliverability): domain to generate SPF/DKIM/DMARC setup for. Replaces the send.
provider	string	optional	Engineer mode: ESP for the SPF include (resend/sendgrid/mailgun/postmark/ses/google). Defaults resend.
dkim_selector	string	optional	Engineer mode: DKIM selector (alphanumeric/hyphen, 1-32). Defaults 'axis'.
dmarc_policy	string	optional	Engineer mode: DMARC policy none\|quarantine\|reject. Defaults none (monitoring).
subject	string	optional	Email subject (max 998 chars, RFC 5322).
body_html	string	optional	HTML body. At least one of body_html / body_text required.
body_text	string	optional	Plaintext body. At least one of body_html / body_text required.
reply_to	string	optional	Optional Reply-To address.

Raw schema

{
  "type": "object",
  "properties": {
    "to": {
      "type": [
        "string",
        "array"
      ],
      "description": "Recipient address or array of addresses (max 50). Required for a send (standard mode)."
    },
    "domain": {
      "type": "string",
      "description": "Engineer mode (Deliverability): domain to generate SPF/DKIM/DMARC setup for. Replaces the send."
    },
    "provider": {
      "type": "string",
      "description": "Engineer mode: ESP for the SPF include (resend/sendgrid/mailgun/postmark/ses/google). Defaults resend."
    },
    "dkim_selector": {
      "type": "string",
      "description": "Engineer mode: DKIM selector (alphanumeric/hyphen, 1-32). Defaults 'axis'."
    },
    "dmarc_policy": {
      "type": "string",
      "description": "Engineer mode: DMARC policy none|quarantine|reject. Defaults none (monitoring)."
    },
    "subject": {
      "type": "string",
      "description": "Email subject (max 998 chars, RFC 5322)."
    },
    "body_html": {
      "type": "string",
      "description": "HTML body. At least one of body_html / body_text required."
    },
    "body_text": {
      "type": "string",
      "description": "Plaintext body. At least one of body_html / body_text required."
    },
    "reply_to": {
      "type": "string",
      "description": "Optional Reply-To address."
    }
  }
}

iliad_llm_inference

AXIS-hosted LLM chat-completion via node-llama-cpp + a small GGUF model loaded in-process. Two input shapes accepted: `prompt` (single string) or `messages` (chat-style array of {role, content}). Sampling controls: `max_tokens` (≤2048), `temperature` (0-2), `top_k`, `top_p`, `seed` (for reproducibility), `stop` (string[]). Inference is fully in-process — no upstream provider, no per-call API fee. Operator sets AXIS_LLM_MODEL_PATH to point at a Phi-3-mini / TinyLlama / Llama-3.2-1B GGUF; if missing, the tool returns a `_not_configured: true` envelope. Engineer mode (X-Agent-Mode: engineer — Constrained Inference, $0.10): pass a `json_schema` and decoding is grammar-constrained to it AND the output is validated against it (returns a `structured` block with valid + parsed + schema_errors) — guaranteed-valid structured output. Requires Authorization: Bearer <api_key>.

Parameters10

prompt	string	optional	Single-prompt completion input. Use either this OR messages, not both.
messages	array	optional	Chat-style input. Array of {role: system\|user\|assistant, content: string}.
system	string	optional	Optional system prompt (prompt mode only). For messages mode, use role=system entries.
max_tokens	number	optional	Max tokens to generate. Defaults 512, hard cap 2048.
temperature	number	optional	Sampling temperature in [0, 2]. Defaults 0.7.
top_k	number	optional	Top-k sampling (positive integer). Defaults 40.
top_p	number	optional	Top-p nucleus sampling in (0, 1]. Defaults 0.95.
seed	number	optional	Optional seed for reproducible output.
stop	array	optional	Stop sequences. Generation halts when any string in the array is produced.
json_schema	object	optional	Engineer mode (required): a JSON Schema. Decoding is grammar-constrained to it and the output is validated against it; returns a `structured` block.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Single-prompt completion input. Use either this OR messages, not both."
    },
    "messages": {
      "type": "array",
      "description": "Chat-style input. Array of {role: system|user|assistant, content: string}."
    },
    "system": {
      "type": "string",
      "description": "Optional system prompt (prompt mode only). For messages mode, use role=system entries."
    },
    "max_tokens": {
      "type": "number",
      "description": "Max tokens to generate. Defaults 512, hard cap 2048."
    },
    "temperature": {
      "type": "number",
      "description": "Sampling temperature in [0, 2]. Defaults 0.7."
    },
    "top_k": {
      "type": "number",
      "description": "Top-k sampling (positive integer). Defaults 40."
    },
    "top_p": {
      "type": "number",
      "description": "Top-p nucleus sampling in (0, 1]. Defaults 0.95."
    },
    "seed": {
      "type": "number",
      "description": "Optional seed for reproducible output."
    },
    "stop": {
      "type": "array",
      "description": "Stop sequences. Generation halts when any string in the array is produced."
    },
    "json_schema": {
      "type": "object",
      "description": "Engineer mode (required): a JSON Schema. Decoding is grammar-constrained to it and the output is validated against it; returns a `structured` block."
    }
  }
}

iliad_code_sandbox

AXIS-owned secure code execution. Each call spawns a fresh ephemeral Docker container with hardened isolation: no network, read-only root filesystem, all Linux capabilities dropped, no-new-privileges, PID/memory/CPU limits, tmpfs /tmp only, runs as nobody:nobody. Container is force-removed after each call. Supports python | node | bash via the multi-runtime image `nikolaik/python-nodejs:python3.12-nodejs22-slim` (operator can override via AXIS_CODE_SANDBOX_IMAGE). Returns stdout/stderr/exit_code/timed_out/duration_ms/image. Wall-clock timeout enforced via SIGKILL + force-remove. Source is fed via stdin (no fs write to the read-only root). Code body capped at 256 KiB; stdin at 1 MiB; timeout 1-600 seconds (default 30); stdout/stderr each capped at 1 MiB output. When no Docker daemon is reachable (Render standard services don't expose /var/run/docker.sock), returns a structured `_not_configured: true` envelope with remediation. Engineer mode (X-Agent-Mode: engineer — Verified Exec, $0.25): the result includes an Ed25519-signed attestation binding code-hash → output-hash + a per-account hash-chain entry, so another agent that pins AXIS's published key can verify the run without re-executing it. Requires Authorization: Bearer <api_key>.

Parameters4

language	string	required	Runtime language.
code	string	required	Source code to execute. Fed via stdin to the interpreter. Max 256 KiB.
timeout_seconds	number	optional	Wall-clock limit. Defaults 30, max 600. SIGKILL on overrun.
stdin	string	optional	Optional additional stdin appended after the code body. Max 1 MiB.

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "type": "string",
      "description": "Runtime language.",
      "enum": [
        "python",
        "node",
        "bash"
      ]
    },
    "code": {
      "type": "string",
      "description": "Source code to execute. Fed via stdin to the interpreter. Max 256 KiB."
    },
    "timeout_seconds": {
      "type": "number",
      "description": "Wall-clock limit. Defaults 30, max 600. SIGKILL on overrun."
    },
    "stdin": {
      "type": "string",
      "description": "Optional additional stdin appended after the code body. Max 1 MiB."
    }
  },
  "required": [
    "language",
    "code"
  ]
}

iliad_document_parsing

AXIS-owned document → Markdown extractor. Accepts either `document_url` (https fetch + 50 MiB cap + 60s timeout) or `document_base64` (inline bytes, 50 MiB decoded cap) — exactly one. Optional `mime_type` hint (application/pdf, application/vnd.openxmlformats-officedocument.wordprocessingml.document, text/html, text/markdown, text/plain); we sniff from magic bytes + URL extension when omitted. Format dispatch: PDF → pdfjs-dist text extraction (one block per page with `--- page N ---` separators); DOCX → mammoth → markdown (tables preserved); HTML → tag-strip with heading + list + entity handling (NOT a full HTML→MD converter — bring turndown if you need fancier); plain text + markdown → passthrough. Returns `{markdown, format_detected, byte_size, page_count, table_count, truncated}`. Output capped at 1 MiB markdown with a truncation marker. Engineer mode (X-Agent-Mode: engineer — Document Intelligence, $0.10): adds an `engineer` block with retrieval chunks (heading-aware, overlapping) + extract-to-caller-schema (pass `json_schema` → a grammar-constrained, validated typed object) + image OCR (image/* via document_base64) — typed data, not just markdown. Requires Authorization: Bearer <api_key>.

Parameters4

document_url	string	optional	https URL to a document. Use this OR document_base64, not both.
document_base64	string	optional	Base64-encoded document bytes. Use this OR document_url, not both.
mime_type	string	optional	Optional MIME-type hint. When omitted we sniff from magic bytes + URL extension. Engineer mode: an image/* mime triggers OCR.
json_schema	object	optional	Engineer mode: a JSON Schema. The document is extracted into a validated object matching it (returned in engineer.extracted).

Raw schema

{
  "type": "object",
  "properties": {
    "document_url": {
      "type": "string",
      "description": "https URL to a document. Use this OR document_base64, not both."
    },
    "document_base64": {
      "type": "string",
      "description": "Base64-encoded document bytes. Use this OR document_url, not both."
    },
    "mime_type": {
      "type": "string",
      "description": "Optional MIME-type hint. When omitted we sniff from magic bytes + URL extension. Engineer mode: an image/* mime triggers OCR."
    },
    "json_schema": {
      "type": "object",
      "description": "Engineer mode: a JSON Schema. The document is extracted into a validated object matching it (returned in engineer.extracted)."
    }
  }
}

iliad_web_search

AXIS-owned BM25 search engine over the corpus YOUR account has indexed. NOT a Google/Bing scraper — agents build their own searchable index by first calling operation='index' with documents (often pages fetched via iliad_web_research), then querying with operation='search'. Five operations: `index` (insert one or many documents), `search` (BM25 top-k ranked hits with snippet + score + metadata), `delete` (drop one doc), `delete_namespace` (drop all), `count`. Namespaces are account-scoped server-side (`acct:<id>:<namespace>`). Persistent across restarts via SQLite. Search supports `max_results` (default 10, max 100) and `site` (restrict to a single URL host, case-insensitive). Engineer mode (X-Agent-Mode: engineer — Answer Engine, $0.25): search also returns a grounded extractive answer with [n] citation spans over your corpus, reranked, refusing on weak evidence. Requires Authorization: Bearer <api_key>.

Parameters8

operation	string	required	index \| search \| delete \| delete_namespace \| count.
namespace	string	optional	Logical isolation key. Defaults 'default'. Account id is always prepended server-side.
document	object	optional	Single document {doc_id, url?, title?, content, metadata?} — used in index mode (alternative to documents[]).
documents	array	optional	Batch of documents (max 100). Transactional — malformed entry aborts the whole call.
query	string	optional	Search query (1-1024 chars). Required in search mode.
max_results	number	optional	Cap on hits returned. Defaults 10, max 100.
site	string	optional	Filter to a single URL host (e.g. 'docs.python.org', case-insensitive).
doc_id	string	optional	Document id to remove. Required in delete mode.

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "description": "index | search | delete | delete_namespace | count.",
      "enum": [
        "index",
        "search",
        "delete",
        "delete_namespace",
        "count"
      ]
    },
    "namespace": {
      "type": "string",
      "description": "Logical isolation key. Defaults 'default'. Account id is always prepended server-side."
    },
    "document": {
      "type": "object",
      "description": "Single document {doc_id, url?, title?, content, metadata?} — used in index mode (alternative to documents[])."
    },
    "documents": {
      "type": "array",
      "description": "Batch of documents (max 100). Transactional — malformed entry aborts the whole call."
    },
    "query": {
      "type": "string",
      "description": "Search query (1-1024 chars). Required in search mode."
    },
    "max_results": {
      "type": "number",
      "description": "Cap on hits returned. Defaults 10, max 100."
    },
    "site": {
      "type": "string",
      "description": "Filter to a single URL host (e.g. 'docs.python.org', case-insensitive)."
    },
    "doc_id": {
      "type": "string",
      "description": "Document id to remove. Required in delete mode."
    }
  },
  "required": [
    "operation"
  ]
}

iliad_text_to_speech

AXIS-owned voice synthesis via Piper (rhasspy/piper) + ffmpeg-static. Accepts `text` (1-5000 chars), optional `voice` slug (filename without extension; defaults to AXIS_PIPER_DEFAULT_VOICE or the first available voice), optional `format` (wav | mp3 | opus; defaults wav), optional `sentence_silence` (0-5 seconds, default 0.2). Returns `{audio_base64, format, voice_used, sample_rate, duration_seconds, byte_size}`. Inference is fully in-process — no upstream provider, no per-character fee. When operator hasn't installed piper or placed voice .onnx + .onnx.json files in AXIS_PIPER_VOICE_DIR (default models/piper/), returns `{_not_configured: true, reason, detail, remediation}`. format=mp3/opus additionally requires ffmpeg-static. Engineer mode (X-Agent-Mode: engineer — Brand Voice, $0.10): pass `brand_text` (a brand / voice-and-tone artifact) and AXIS auto-derives the voice persona (Piper voice slug + sentence pacing) and synthesizes in it; the persona is echoed in the response. Requires Authorization: Bearer <api_key>.

Parameters7

text	string	required	Text to speak. 1-5000 chars after trim.
voice	string	optional	Voice slug (filename without extension, e.g. 'en_US-amy-medium'). Defaults to first available voice or AXIS_PIPER_DEFAULT_VOICE.
format	string	optional	Audio codec.
sentence_silence	number	optional	Per-sentence silence in seconds (0-5). Defaults 0.2.
brand_text	string	optional	Engineer mode: brand / voice-and-tone artifact. AXIS derives a voice persona from it and synthesizes in that voice (overrides voice/sentence_silence).
locale	string	optional	Engineer mode: persona locale override.
gender	string	optional	Engineer mode: persona gender override.

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to speak. 1-5000 chars after trim."
    },
    "voice": {
      "type": "string",
      "description": "Voice slug (filename without extension, e.g. 'en_US-amy-medium'). Defaults to first available voice or AXIS_PIPER_DEFAULT_VOICE."
    },
    "format": {
      "type": "string",
      "description": "Audio codec.",
      "enum": [
        "wav",
        "mp3",
        "opus"
      ]
    },
    "sentence_silence": {
      "type": "number",
      "description": "Per-sentence silence in seconds (0-5). Defaults 0.2."
    },
    "brand_text": {
      "type": "string",
      "description": "Engineer mode: brand / voice-and-tone artifact. AXIS derives a voice persona from it and synthesizes in that voice (overrides voice/sentence_silence)."
    },
    "locale": {
      "type": "string",
      "description": "Engineer mode: persona locale override.",
      "enum": [
        "us",
        "gb"
      ]
    },
    "gender": {
      "type": "string",
      "description": "Engineer mode: persona gender override.",
      "enum": [
        "female",
        "male"
      ]
    }
  },
  "required": [
    "text"
  ]
}

iliad_speech_to_text

AXIS-owned audio transcription via whisper.cpp + ffmpeg-static. Accepts either `audio_url` (https URL we fetch, max 100 MiB, 60s download timeout) or `audio_base64` (inline bytes, max 100 MiB decoded) — exactly one. Accepts any audio format ffmpeg can decode (mp3, wav, m4a, opus, ogg, flac); we resample to 16 kHz mono WAV internally. Optional `language` (ISO-639-1 like "en" / "fr" / "ja", or "auto" — default). Optional `initial_prompt` (≤512 chars; biases spelling of rare names). Optional `word_timestamps` boolean. Returns `{text, segments: [{start, end, text}], language_detected, duration_seconds, model_used}`. When operator hasn't installed whisper-cli or placed the GGML model file at AXIS_WHISPER_MODEL_PATH (default `models/ggml-base.en.bin`), returns `{_not_configured: true, reason, detail, remediation}`. Engineer mode (X-Agent-Mode: engineer — Diarization, $0.10): the response adds `diarization` — speaker turns grouped from the segments by inter-segment pause gaps (tune with diarization_gap_seconds / max_speakers; this is pause-based turn segmentation, not acoustic speaker ID). Requires Authorization: Bearer <api_key>.

Parameters7

audio_url	string	optional	https URL to an audio file. Use this OR audio_base64, not both.
audio_base64	string	optional	Base64-encoded audio bytes. Use this OR audio_url, not both.
language	string	optional	ISO-639-1 language code (en, fr, ja, ...) or 'auto' to autodetect. Defaults 'auto'.
initial_prompt	string	optional	Optional bias prompt (≤512 chars) — useful for spelling of rare names.
word_timestamps	boolean	optional	Emit word-level timestamps within segments. Defaults false.
diarization_gap_seconds	number	optional	Engineer mode: pause (seconds) between segments that starts a new speaker turn. Defaults 0.75.
max_speakers	number	optional	Engineer mode: max alternating speaker labels. Defaults 2.

Raw schema

{
  "type": "object",
  "properties": {
    "audio_url": {
      "type": "string",
      "description": "https URL to an audio file. Use this OR audio_base64, not both."
    },
    "audio_base64": {
      "type": "string",
      "description": "Base64-encoded audio bytes. Use this OR audio_url, not both."
    },
    "language": {
      "type": "string",
      "description": "ISO-639-1 language code (en, fr, ja, ...) or 'auto' to autodetect. Defaults 'auto'."
    },
    "initial_prompt": {
      "type": "string",
      "description": "Optional bias prompt (≤512 chars) — useful for spelling of rare names."
    },
    "word_timestamps": {
      "type": "boolean",
      "description": "Emit word-level timestamps within segments. Defaults false."
    },
    "diarization_gap_seconds": {
      "type": "number",
      "description": "Engineer mode: pause (seconds) between segments that starts a new speaker turn. Defaults 0.75."
    },
    "max_speakers": {
      "type": "number",
      "description": "Engineer mode: max alternating speaker labels. Defaults 2."
    }
  }
}

iliad_analytics

AXIS-owned product analytics. Two operations: `capture` (insert events) and `query` (aggregations). Capture accepts a single `event` or a batch via `events[]` (max 500). Query kinds: `count` (total events), `count_by_event` (top events by frequency), `distinct_users` (unique user_id count), `count_by_bucket` (time-series with minute/hour/day buckets). All queries support optional `event`, `from_ts`, `to_ts`, and `property_filter` filters. Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`). Persistent across restarts via SQLite. Requires Authorization: Bearer <api_key>. Best for funnels, cohorts, and retention on workloads up to ~1M events per account.

Parameters5

operation	string	required	capture or query.
namespace	string	optional	Logical isolation key. Defaults to 'default'. Account id is always prepended server-side.
event	object	optional	Single event payload {event, user_id?, properties?, timestamp?} — used in capture mode.
events	array	optional	Batch of event payloads (max 500). Transactional — partial inserts never persist.
query	object	optional	{kind, event?, from_ts?, to_ts?, property_filter?, bucket?, limit?} — used in query mode.

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "description": "capture or query.",
      "enum": [
        "capture",
        "query"
      ]
    },
    "namespace": {
      "type": "string",
      "description": "Logical isolation key. Defaults to 'default'. Account id is always prepended server-side."
    },
    "event": {
      "type": "object",
      "description": "Single event payload {event, user_id?, properties?, timestamp?} — used in capture mode."
    },
    "events": {
      "type": "array",
      "description": "Batch of event payloads (max 500). Transactional — partial inserts never persist."
    },
    "query": {
      "type": "object",
      "description": "{kind, event?, from_ts?, to_ts?, property_filter?, bucket?, limit?} — used in query mode."
    }
  },
  "required": [
    "operation"
  ]
}

iliad_hygiene

AXIS-owned workspace hygiene grader. Analyzes an inline file set [{path,content}] and returns a letter grade (A-F) across a closed set of dimensions plus structured findings. Two modes: mode='scan' (DEFAULT, FREE) returns grade + findings (committed-secret scan, .env/secret-file detection, .gitignore gaps for build/scratch artifacts, oversized blobs, stub/placeholder markers, byte-identical duplicate files, source test-peer coverage, TODO/FIXME debt); mode='fix' (METERED, paid) adds a prioritized remediation plan with ready-to-apply .gitignore additions and per-finding actions. Deterministic, dependency-free, never mutates your repo (fix returns a PLAN). Rules needing a live git checkout/toolchain (worktree pruning, build/vet, route-registration dup-handler analysis) are reported as repo_only_rules, not run. Engineer mode (X-Agent-Mode: engineer — Security Engineer, $5): the fix arrives as a git-applyable unified-diff patch + a SARIF 2.1.0 log for CI code-scanning. Requires Authorization: Bearer <api_key>.

Parameters3

files	array	required	Inline files [{path, content}] to scan (non-empty; each content <= 5 MB).
mode	string	optional	scan (free grade+findings, default) \| fix (metered, adds remediation plan).
config	object	optional	Optional threshold overrides: maxFileBytes, coverageA, coverageB, coverageC, todoDebtThreshold.

Raw schema

{
  "type": "object",
  "properties": {
    "files": {
      "type": "array",
      "description": "Inline files [{path, content}] to scan (non-empty; each content <= 5 MB)."
    },
    "mode": {
      "type": "string",
      "description": "scan (free grade+findings, default) | fix (metered, adds remediation plan).",
      "enum": [
        "scan",
        "fix"
      ]
    },
    "config": {
      "type": "object",
      "description": "Optional threshold overrides: maxFileBytes, coverageA, coverageB, coverageC, todoDebtThreshold."
    }
  },
  "required": [
    "files"
  ]
}

sca_exemption_decision

Decide the lighter-SCA path for a single transaction using AXIS's published 7-priority PSD2 exemption matrix (the same decideScaExemption engine that renders the SCA Exemption Decision Matrix in generated artifacts). Input: amount_eur (required, PSD2 thresholds are EUR-denominated — convert before calling) plus optional context flags (secure corporate program, MIT, fixed recurring + prior SCA, trusted beneficiary + prior SCA, one-leg-out, acquirer TRA fraud rate in basis points). Returns the chosen exemption, its priority, sca_required, rationale, fallback path, all applicable candidates, the rendered priority matrix, and a sha256 reproducibility proof. Free, no auth, deterministic, no side effects. HONESTY: decision-support only, NOT an authorization oracle — final exemption eligibility is decided by the acquirer/issuer; TRA caps use published EBA RTS Art. 15 bands, not your acquirer's live fraud rate.

Parameters8

amount_eur	number	required	Transaction amount in EUR (PSD2 thresholds are EUR-denominated).
is_secure_corporate	boolean	optional	Dedicated/lodged corporate card program (RTS Art. 16).
is_merchant_initiated	boolean	optional	MIT with stored credential + original SCA reference (out of SCA scope).
is_recurring_fixed	boolean	optional	Fixed-amount subsequent collection (RTS Art. 13). Requires has_prior_sca.
is_trusted_beneficiary	boolean	optional	Merchant on the cardholder's trusted list (RTS Art. 12). Requires has_prior_sca.
is_one_leg_out	boolean	optional	Payer or payee outside the EEA (territorial scope, not a formal exemption).
has_prior_sca	boolean	optional	A prior SCA exists — gates recurring_fixed and trusted_beneficiary.
tra_acquirer_fraud_bps	number	optional	Acquirer reference fraud rate in basis points (EBA RTS Art. 15 bands: <=1 → €500 cap, <=6 → €250, <=13 → €100).

Raw schema

{
  "type": "object",
  "properties": {
    "amount_eur": {
      "type": "number",
      "description": "Transaction amount in EUR (PSD2 thresholds are EUR-denominated)."
    },
    "is_secure_corporate": {
      "type": "boolean",
      "description": "Dedicated/lodged corporate card program (RTS Art. 16)."
    },
    "is_merchant_initiated": {
      "type": "boolean",
      "description": "MIT with stored credential + original SCA reference (out of SCA scope)."
    },
    "is_recurring_fixed": {
      "type": "boolean",
      "description": "Fixed-amount subsequent collection (RTS Art. 13). Requires has_prior_sca."
    },
    "is_trusted_beneficiary": {
      "type": "boolean",
      "description": "Merchant on the cardholder's trusted list (RTS Art. 12). Requires has_prior_sca."
    },
    "is_one_leg_out": {
      "type": "boolean",
      "description": "Payer or payee outside the EEA (territorial scope, not a formal exemption)."
    },
    "has_prior_sca": {
      "type": "boolean",
      "description": "A prior SCA exists — gates recurring_fixed and trusted_beneficiary."
    },
    "tra_acquirer_fraud_bps": {
      "type": "number",
      "description": "Acquirer reference fraud rate in basis points (EBA RTS Art. 15 bands: <=1 → €500 cap, <=6 → €250, <=13 → €100)."
    }
  },
  "required": [
    "amount_eur"
  ]
}

grade_compliance

Run the real 8-check AP2/Visa compliance grading engine (gradeCompliance — the same engine behind computeComplianceGrade and the commerce registry's verified_decisions block) over an inline file set. Each of the 8 validators (SCA/3DS2 readiness, AP2 mandate validity, tokenization posture, CE 3.0 readiness, dispute rail wiring, idempotency/receipt hygiene, budget negotiation, refund/cancel path) is a multi-signal check with weight, evidence trail, and remediation. Returns grade A-D, score, checks_passed/8, the full checks[] detail, detected commerce signals, and a sha256 reproducibility proof. Free, no auth, deterministic, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. HONESTY: deterministic static source-signal analysis — a checklist starting point, NOT a certification, audit, PCI assessment, or card-network certification.

Parameters1

files

array

required

Source files to grade (max 25 files, 50KB each, 1MB total)

Raw schema

{
  "type": "object",
  "properties": {
    "files": {
      "type": "array",
      "description": "Source files to grade (max 25 files, 50KB each, 1MB total)",
      "items": {
        "type": "object",
        "required": [
          "path",
          "content"
        ],
        "properties": {
          "path": {
            "type": "string"
          },
          "content": {
            "type": "string"
          }
        }
      }
    }
  },
  "required": [
    "files"
  ]
}

assemble_ce3_evidence

Assemble a Visa Compelling Evidence 3.0 packet + eligibility verdict for a disputed card-absent-fraud (reason code 10.4) transaction using the real assembleCe3 engine: finds prior undisputed transactions in the caller-supplied history that share >=2 qualified data elements (device_id / ip_address / email / shipping_address / login_id) and fall 120-365 days before the disputed transaction, per CE 3.0 rules. Returns {eligible, qualifying_priors, matched_element_union, rejection_reason?, evidence_packet, caveat} plus a sha256 reproducibility proof. Free, no auth, deterministic, no side effects. HONESTY: CE 3.0 applies to reason code 10.4 ONLY (10.2/10.3 are card-present conditions), and this is ASSEMBLY ONLY — not a submission to VROL/Verifi (use assemble_representment for the Stripe representment path). AXIS does not publish win-rate estimates.

Parameters2

dispute	object	required	{txn: {id, amount_minor, currency, created_at, disputed, device_id?, ip_address?, email?, shipping_address?, login_id?}, reason_code: string (CE 3.0 requires '10.4'), disputed_at: ISO timestamp}
transaction_history	array	optional	Candidate prior transactions (same Txn shape, max 500). Undisputed priors sharing >=2 qualified elements qualify.

Raw schema

{
  "type": "object",
  "properties": {
    "dispute": {
      "type": "object",
      "description": "{txn: {id, amount_minor, currency, created_at, disputed, device_id?, ip_address?, email?, shipping_address?, login_id?}, reason_code: string (CE 3.0 requires '10.4'), disputed_at: ISO timestamp}"
    },
    "transaction_history": {
      "type": "array",
      "description": "Candidate prior transactions (same Txn shape, max 500). Undisputed priors sharing >=2 qualified elements qualify."
    }
  },
  "required": [
    "dispute"
  ]
}

build_ap2_mandate

Validate, canonically encode, and optionally Ed25519-sign an AP2 mandate (Intent / Cart / Payment) using the real @axis/ap2 codecs — schema validation (including cart-total arithmetic and intent cross-references), RFC 8785 JCS-style canonical JSON encoding, and detached-JWS EdDSA signing over node:crypto. Pass seed_hex (64 hex chars = 32 bytes) to sign deterministically client-side-supplied key material — AXIS stores no keys; omit it for an unsigned template with encoding only. The signed envelope round-trips through verifyMandate before it is returned. Free, no auth, deterministic (Ed25519 signatures are deterministic per RFC 8032), no side effects. SCOPE HONESTY: conformant to AXIS's TypeScript encoding of the public AP2 mandate schema, verified against self-authored golden vectors — NOT certified against an official AP2 conformance suite or a live network counterparty.

Parameters3

mandate	object	required	An AP2 mandate object: {kind: 'intent'\|'cart'\|'payment', version: 'ap2/1', id, created_at, ...kind-specific fields (intent: user_id/description/constraints.max_amount/expires_at; cart: intent_ref/merchant_id/items[]/total; payment: cart_ref/method/amount)}.
seed_hex	string	optional	Optional 64-char hex (32-byte) Ed25519 seed to sign with. Caller-supplied key material — AXIS stores no keys. Omit for an unsigned template.
intent_context	object	optional	Optional IntentMandate to cross-reference a cart's intent_ref against.

Raw schema

{
  "type": "object",
  "properties": {
    "mandate": {
      "type": "object",
      "description": "An AP2 mandate object: {kind: 'intent'|'cart'|'payment', version: 'ap2/1', id, created_at, ...kind-specific fields (intent: user_id/description/constraints.max_amount/expires_at; cart: intent_ref/merchant_id/items[]/total; payment: cart_ref/method/amount)}."
    },
    "seed_hex": {
      "type": "string",
      "description": "Optional 64-char hex (32-byte) Ed25519 seed to sign with. Caller-supplied key material — AXIS stores no keys. Omit for an unsigned template."
    },
    "intent_context": {
      "type": "object",
      "description": "Optional IntentMandate to cross-reference a cart's intent_ref against."
    }
  },
  "required": [
    "mandate"
  ]
}

score_dispute_readiness

Score how ready a disputed transaction's EVIDENCE FILE is for representment, per Visa reason-code family, using the transparent scoreWinProbability heuristic (win-prob-v0: hand-set, documented logistic coefficients — exported, inspectable, monotonic in evidence). Input: reason_code + the evidence on file (CE 3.0 eligibility, matching data elements, prior undisputed transactions, delivery proof, AVS/CVV, 3DS, signed mandate, customer communication). Returns the heuristic score, band, top missing evidence (what to capture next), recommended action, rationale, model version, and a sha256 reproducibility proof. Free, no auth, deterministic. HONESTY (read this): this scores evidence-capture readiness and is NOT a dispute-win prediction — the v0 heuristic is NOT empirically calibrated against real network outcomes, is NOT a Visa-published or Visa-endorsed win rate, and AXIS does not publish win-rate estimates. Treat it as a prioritization signal for evidence gathering only; always follow your operator's dispute policy.

Parameters2

reason_code	string	required	Visa dispute reason code (e.g. '10.4', '13.1', '12.5'). Unknown codes fall back to a documented default family.
evidence	object	optional	Evidence on file: {ce3Eligible?, matchingDataElements? (0-5), priorUndisputedTransactions? (0-10), hasDeliveryProof?, hasAvsMatch?, hasCvvMatch?, has3dsAuthenticated?, hasSignedMandate?, hasCustomerCommunication?}. Omitted fields default to false/0.

Raw schema

{
  "type": "object",
  "properties": {
    "reason_code": {
      "type": "string",
      "description": "Visa dispute reason code (e.g. '10.4', '13.1', '12.5'). Unknown codes fall back to a documented default family."
    },
    "evidence": {
      "type": "object",
      "description": "Evidence on file: {ce3Eligible?, matchingDataElements? (0-5), priorUndisputedTransactions? (0-10), hasDeliveryProof?, hasAvsMatch?, hasCvvMatch?, has3dsAuthenticated?, hasSignedMandate?, hasCustomerCommunication?}. Omitted fields default to false/0."
    }
  },
  "required": [
    "reason_code"
  ]
}

assemble_representment

Turn a webhook-ingested dispute (charge.dispute.* events persist DisputeRecords server-side) into a Stripe representment: qualifies CE 3.0 priors from your supplied transaction history (assembleCe3), builds the Stripe `evidence` hash (buildStripeRepresentment), walks the dispute state machine (needs_response → evidence_assembling → evidence_submitted) with a full transition ledger, and — when submit=true and Stripe is configured — submits the evidence through the live Stripe disputes API. Requires Authorization: Bearer <api_key>; metered ($0.50 standard, $0.25 lite) through the standard authorize/capture path — a failed assembly never charges. Returns {dispute, evidence, ce3, ce3_eligible, submitted, disclaimer}. HONESTY: the dispute lifecycle is LIVE on the Stripe rail only; VROL/RDR/CDRN (Verifi/Ethoca) is integration-ready code gated on acquirer provisioning (AXIS_ENABLE_VROL) and never fakes a submission. AXIS does not publish win-rate estimates.

Parameters5

dispute_id	string	required	Provider dispute id (Stripe dp_...) previously ingested by the charge.dispute.created webhook.
disputed_txn	object	optional	Optional CE 3.0 data elements of the disputed transaction: {device_id?, ip_address?, email?, shipping_address?, login_id?}.
transaction_history	array	optional	Candidate prior transactions for CE 3.0 qualification (Txn shape, max 500).
evidence_inputs	object	optional	{customerEmail?, shippingAddress?, billingAddress?, serviceDate?, productDescription?, deliveryTracking?, threeDsAuthenticated?} — merchant-supplied evidence fields.
submit	boolean	optional	true → submit the built evidence to the Stripe disputes API (requires STRIPE_SECRET_KEY server-side). Default false (assemble only).

Raw schema

{
  "type": "object",
  "properties": {
    "dispute_id": {
      "type": "string",
      "description": "Provider dispute id (Stripe dp_...) previously ingested by the charge.dispute.created webhook."
    },
    "disputed_txn": {
      "type": "object",
      "description": "Optional CE 3.0 data elements of the disputed transaction: {device_id?, ip_address?, email?, shipping_address?, login_id?}."
    },
    "transaction_history": {
      "type": "array",
      "description": "Candidate prior transactions for CE 3.0 qualification (Txn shape, max 500)."
    },
    "evidence_inputs": {
      "type": "object",
      "description": "{customerEmail?, shippingAddress?, billingAddress?, serviceDate?, productDescription?, deliveryTracking?, threeDsAuthenticated?} — merchant-supplied evidence fields."
    },
    "submit": {
      "type": "boolean",
      "description": "true → submit the built evidence to the Stripe disputes API (requires STRIPE_SECRET_KEY server-side). Default false (assemble only)."
    }
  },
  "required": [
    "dispute_id"
  ]
}

iliad_network_tokenization

Network-tokenization capability with three honest parts. (1) `lifecycle`: an EXECUTABLE TAP-style token-lifecycle state machine (provision → activate → suspend → resume → delete; deleted is terminal; illegal transitions are rejected with an error, not silently accepted). (2) `read` — the LIVE default: reads a Stripe PaymentMethod (GET /v1/payment_methods/{id} with the operator's STRIPE_SECRET_KEY) and maps it to a provider-agnostic NetworkToken; `is_network_token` is true ONLY when Stripe reports a provisioned network token (card.network_token.used) — a bare card PM honestly reads false, and co-badging metadata (card.networks.available) is never treated as a tokenization signal. (3) `provision` with provider vts|mdes: capability-gated behind a network-issued Token Requestor ID (AXIS_VTS_TOKEN_REQUESTOR_ID / AXIS_MDES_TOKEN_REQUESTOR_ID); returns a structured `_not_configured: true` envelope naming the exact missing gate until Visa/Mastercard onboarding exists — it NEVER fakes a token (provider stripe delegates to `read`). `capabilities` reports which providers are configured. Raw PANs are never accepted (pan_source is an opaque reference), keeping PCI-DSS scope out of this service. Free (unmetered); requires Authorization: Bearer <api_key>.

Parameters6

operation	string	optional	read (default) \| provision \| lifecycle \| capabilities.
payment_method_id	string	optional	read: the Stripe PaymentMethod id (pm_…) to read the network-token status of.
provider	string	optional	provision: stripe \| vts \| mdes. stripe delegates to read (Stripe provisions tokens itself); vts/mdes are capability-gated.
pan_source	string	optional	provision: an OPAQUE payment-credential reference (e.g. a Stripe pm_… id). NEVER a raw PAN — raw card numbers are rejected by policy.
events	array	optional	lifecycle: ordered TokenEvent list (provision\|activate\|suspend\|resume\|delete), max 100. Must start from provision; illegal transitions throw.
event	string	optional	lifecycle: single-event shorthand for `events: [event]`.

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "description": "read (default) | provision | lifecycle | capabilities.",
      "enum": [
        "read",
        "provision",
        "lifecycle",
        "capabilities"
      ]
    },
    "payment_method_id": {
      "type": "string",
      "description": "read: the Stripe PaymentMethod id (pm_…) to read the network-token status of."
    },
    "provider": {
      "type": "string",
      "description": "provision: stripe | vts | mdes. stripe delegates to read (Stripe provisions tokens itself); vts/mdes are capability-gated.",
      "enum": [
        "stripe",
        "vts",
        "mdes"
      ]
    },
    "pan_source": {
      "type": "string",
      "description": "provision: an OPAQUE payment-credential reference (e.g. a Stripe pm_… id). NEVER a raw PAN — raw card numbers are rejected by policy."
    },
    "events": {
      "type": "array",
      "description": "lifecycle: ordered TokenEvent list (provision|activate|suspend|resume|delete), max 100. Must start from provision; illegal transitions throw."
    },
    "event": {
      "type": "string",
      "description": "lifecycle: single-event shorthand for `events: [event]`."
    }
  }
}

README.md20 KBView on GitHub

Axis' Iliad

Axis' Iliad — The modern epic that shapes raw codebases into canonical, agent-ready artifacts. Axis' Iliad authors the definitive foundation for the next era of natural-language workspace development.

Canonical name: Axis' Iliad. Use this name consistently across docs, registries, and integrations.

AXIS Ecosystem

Iliad is the x402 showcase in the Trust Fabric stack. Full registry: packages/generator-core/src/estate-registry.ts, served live at GET /.well-known/axis-estate.json (superseding ecosystem.registry.yaml, retired 2026-08-22 — see docs/ESTATE_FEDERATION_STRATEGY.md).

Project	Role	x402
Axis' Iliad (this repo)	Agent artifacts + MCP gateway	Wired — `@axis/mpp`
PAID	Multi-rail payments + settlement	Settlement layer (planned Go x402)
AXIS Foundry	3D pipeline + MCP	Partial
Trust Fabric	Compliance audit, remediation + Trust Passport	Planned

x402 contract: docs/x402/CONTRACT.md

Every program ships free artifacts with no API key — 47 of the 152 in total. Three programs are free in full:

bash

# 1. Get an API key (free tier, instant)
curl -X POST https://api.iliad.trustfabric.ai/v1/accounts \
  -H 'Content-Type: application/json' \
  -d '{"email":"you@example.com","name":"My Agent","tier":"free"}'

# 2. Analyze any public GitHub repo
curl -X POST https://api.iliad.trustfabric.ai/v1/github/analyze \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{"url":"https://github.com/owner/repo","programs":["search","skills","debug"]}'

# 3. Download the generated artifacts as a ZIP
curl https://api.iliad.trustfabric.ai/v1/projects/PROJECT_ID/export \
  -H 'Authorization: Bearer YOUR_API_KEY' -o artifacts.zip

Free tier includes: 47 artifacts spanning all 21 programs — Search (context maps), Skills (AGENTS.md, CLAUDE.md, .cursorrules) and Debug (playbooks, incident templates) in full, plus each other program's headline artifact (design tokens, Dockerfile, MCP config, brand guidelines, ...). Paying unlocks each program's remaining artifacts.

What you get

One scan → 152 artifacts across 21 programs, ready in seconds:

What you need	Program	Key outputs
Orient a new AI agent	Search (free)	`context-map.json`, `repo-profile.yaml`, `architecture-summary.md`
Give any LLM codebase context	Skills (free)	`AGENTS.md`, `CLAUDE.md`, `.cursorrules`, `workflow-pack.md`
Debug a production incident	Debug (free)	`debug-playbook.md`, `tracing-rules.md`, `root-cause-checklist.md`
Audit your UI	Frontend	`frontend-rules.md`, `ui-audit.md`, `component-guidelines.md`
Fix search ranking	SEO	`seo-rules.md`, `meta-tag-audit.json`, `schema-recommendations.json`
Cut LLM costs	Optimization	`optimization-rules.md`, `cost-estimate.json`, `token-budget-plan.md`
Ship a design system	Theme	`design-tokens.json`, `theme.css`, `dark-mode-tokens.json`
Unify your brand voice	Brand	`brand-guidelines.md`, `voice-and-tone.md`, `messaging-system.yaml`
Automate dev workflows	Superpowers	`superpower-pack.md`, `workflow-registry.json`, `automation-pipeline.yaml`
Launch a campaign	Marketing	`campaign-brief.md`, `funnel-map.md`, `ab-test-plan.md`
Build data/research tools	Notebook	`notebook-summary.md`, `research-threads.md`, `source-map.json`
Manage a knowledge vault	Obsidian	`obsidian-skill-pack.md`, `vault-rules.md`, `graph-prompt-map.json`
Connect AI tools (MCP)	MCP	`mcp-config.json`, `mcp-registry-metadata.json`, `protocol-spec.md`, `spec.types.ts`, `mcp/README.md`, `mcp/project-setup.md`, `mcp/build-artifacts.md`, `mcp/package-json.root.template.json`, `mcp/package-json.package.template.json`, `mcp/tsconfig.root.template.json`, `mcp/tsconfig.package.template.json`, `mcp/monorepo-structure.md`, `mcp/core-implementation-artifacts.md`, `mcp/testing-documentation-polish-artifacts.md`, `mcp/fintech-mcp-surface-package.md`, `mcp/fintech-domain-schema.yaml`, `connector-map.yaml`, `capability-registry.json`, `server-manifest.yaml`
Generate components	Artifacts	`generated-component.tsx`, `dashboard-widget.tsx`, `component-library.json`
Create dev videos	Remotion	`remotion-script.ts`, `scene-plan.md`, `storyboard.md`
Social & visual assets	Canvas	`canvas-spec.json`, `social-pack.md`, `poster-layouts.md`
Generative art / NFT	Algorithmic	`generative-sketch.ts`, `variation-matrix.json`, `parameter-pack.json`
Agentic commerce (Visa AP2)	Agentic Purchasing	`agent-purchasing-playbook.md`, `checkout-flow.md`, `negotiation-rules.md`

Plus the begin loop — hand it to an agent and say `begin`

Every analysis also weaves in a self-driving control loop so an AI coding agent can finish the work, not just understand it:

begin.yaml — the loop head: the inferred goal, a human-in-the-loop protocol (the owner only answers plain-English product questions), the move-selection algorithm, and convergent stop conditions.
continuation.yaml — the loop state: an ordered step-list of every artifact + a priority candidate queue seeded from the analysis (the goal, detected gaps, a verify-harness when no tests exist).
A ⟳ Continue footer on every Markdown artifact; the final step self-prompts begin, closing the loop back to begin.yaml.

Download the pack (CLI, MCP, or the full-pack export), hand it to an agent, say begin — it works the queue, verifies each step, and stops when the queue is empty (convergent, never a runaway). No coding required on the owner's end.

AXIS dogfoods this on itself: this repo's own root begin.yaml / continuation.yaml are the live loop we work from, also served verbatim over REST at GET /begin.yaml / GET /continuation.yaml — so an agent crawling this API discovers the same convention without cloning the repo.

For AI agents — MCP integration

AXIS exposes a Streamable HTTP MCP server at https://api.iliad.trustfabric.ai/mcp. Add it to your agent and it can analyze any repo or prepare for agentic purchasing autonomously.

VS Code (.vscode/mcp.json):

json

{
  "servers": {
    "axis-iliad": {
      "type": "http",
      "url": "https://api.iliad.trustfabric.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Claude Desktop (claude_desktop_config.json):

json

{
  "mcpServers": {
    "axis-iliad": {
      "url": "https://api.iliad.trustfabric.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Free MCP tools (no auth needed): list_programs, search_and_discover_tools, get_install_manifest, discover_agentic_purchasing_needs, prepare_agentic_purchasing_preview, discover_estate_tools (sibling AXIS properties — payments, 3D generation, and more), plus the deterministic commerce decision engines: sca_exemption_decision, grade_compliance, assemble_ce3_evidence, build_ap2_mandate, score_dispute_readiness (evidence-capture readiness — not a dispute-win prediction). Five more are estate-flagged planned-capability stubs (Foundry Wave-1, honest redirects to Foundry's own MCP endpoint until an Iliad-hosted proxy ships): axis_validate, axis_inspect, axis_compare, axis_manifest_verify, roblox_compliance_check. get_referral_code, get_referral_credits, and iliad_network_tokenization are also free (no charge) but, unlike the tools above, do require auth. ping_payment is not free — it costs $0.01 and exercises the real x402 payment loop, the cheapest paid call in the catalog.

Pricing

Tier	Price	Programs
Free	$0	47 artifacts across all 21 programs (Search, Skills, Debug in full)
Pro	$3.00 / run	All 21 programs, 152 artifacts
Lite mode	$0.15–$0.25 / run	Top-gap summary, reduced output

Budget negotiation: send X-Agent-Budget: {"budget_per_run_cents": 25} + X-Agent-Mode: lite on any paid call.

Self-host

System Requirements

Node.js: ≥ 20.x (LTS recommended)
pnpm: ≥ 9.x
OS: macOS 11+, Linux (any distro), or Windows 10+
RAM: 4 GB minimum (8 GB recommended)
Disk space: ~2 GB for dependencies + build

Quick Start

bash

# Prerequisites: Node.js ≥ 20, pnpm ≥ 9
git clone https://github.com/lastmanupinc-hub/axis-iliad.git
cd axis-iliad
pnpm install
pnpm build

# Start the API server (port 4000)
node apps/api/dist/server.js

# Start the web UI (port 5173)
cd apps/web && npx vite

# Or use the CLI directly
node apps/cli/dist/cli.js analyze .
node apps/cli/dist/cli.js github https://github.com/owner/repo

Docker

bash

docker build -t axis-iliad .
docker run -p 4000:4000 axis-iliad

Requires: Docker 20.10+ or Docker Desktop

Architecture

code

axis-iliad/
├── apps/
│   ├── api/          → Zero-dependency HTTP server (port 4000, 188 endpoints)
│   ├── cli/          → CLI tool: axis analyze <dir> | axis github <url>
│   └── web/          → Vite + React 19 SPA (dark theme, toast, command palette)
├── packages/
│   ├── snapshots/    → Snapshot intake, Postgres (Neon) persistence, billing, funnel
│   ├── repo-parser/  → Language detection (60+), framework detection (10), import graph
│   ├── context-engine/ → Context map builder, repo profile, route/architecture analysis
│   └── generator-core/ → 152 generators across 21 programs
└── vitest.config.ts  → Shared test config

Programs (21)

Program	Outputs	Tier
Search	context-map.json, repo-profile.yaml, architecture-summary.md, dependency-hotspots.md	Free
Skills	AGENTS.md, CLAUDE.md, .cursorrules, workflow-pack.md, policy-pack.md	Free
Debug	debug-playbook.md, incident-template.md, tracing-rules.md, root-cause-checklist.md	Free
Frontend	frontend-rules.md, component-guidelines.md, layout-patterns.md, ui-audit.md	Pro
SEO	seo-rules.md, schema-recommendations.json, route-priority-map.md, content-audit.md, meta-tag-audit.json	Pro
Optimization	optimization-rules.md, prompt-diff-report.md, cost-estimate.json, token-budget-plan.md	Pro
Theme	design-tokens.json, theme.css, theme-guidelines.md, component-theme-map.json, dark-mode-tokens.json	Pro
Brand	brand-guidelines.md, voice-and-tone.md, content-constraints.md, messaging-system.yaml, channel-rulebook.md	Pro
Superpowers	superpower-pack.md, workflow-registry.json, test-generation-rules.md, refactor-checklist.md, automation-pipeline.yaml	Pro
Marketing	campaign-brief.md, funnel-map.md, sequence-pack.md, cro-playbook.md, ab-test-plan.md	Pro
Notebook	notebook-summary.md, source-map.json, study-brief.md, research-threads.md, citation-index.json	Pro
Obsidian	obsidian-skill-pack.md, vault-rules.md, graph-prompt-map.json, linking-policy.md, template-pack.md	Pro
MCP	mcp-config.json, mcp-registry-metadata.json, protocol-spec.md, connector-map.yaml, capability-registry.json, server-manifest.yaml	Pro
Artifacts	generated-component.tsx, dashboard-widget.tsx, embed-snippet.ts, artifact-spec.md, component-library.json	Pro
Remotion	remotion-script.ts, scene-plan.md, render-config.json, asset-checklist.md, storyboard.md	Pro
Canvas	canvas-spec.json, social-pack.md, poster-layouts.md, asset-guidelines.md, brand-board.md	Pro
Algorithmic	generative-sketch.ts, parameter-pack.json, collection-map.md, export-manifest.yaml, variation-matrix.json	Pro
Agentic Purchasing	agent-purchasing-playbook.md, product-schema.json, checkout-flow.md, negotiation-rules.md, commerce-registry.json	Pro
Closer	packaging/README.md, Dockerfile, .github/workflows/ci.yml, packaging-report.md, DISTRIBUTABLE.md, Makefile	Pro
Deploy	deploy/Dockerfile, deploy/render.yaml, deploy/deploy.sh, deploy/worker.ts, deploy-qualification-report.md	Pro

API Endpoints

Core Pipeline

Method	Path	Description
POST	`/v1/snapshots`	Upload repo snapshot (multipart file upload)
POST	`/v1/github/analyze`	Analyze repo from GitHub URL
GET	`/v1/snapshots/:id`	Get snapshot metadata
GET	`/v1/projects/:project_id/snapshots`	List snapshots for project
POST	`/v1/search/export`	Run search program
POST	`/v1/skills/generate`	Run skills program
POST	`/v1/debug/analyze`	Run debug program
POST	`/v1/frontend/audit`	Run frontend program
POST	`/v1/seo/analyze`	Run SEO program
POST	`/v1/optimization/analyze`	Run optimization program
POST	`/v1/theme/generate`	Run theme program
POST	`/v1/brand/generate`	Run brand program
POST	`/v1/superpowers/generate`	Run superpowers program
POST	`/v1/marketing/generate`	Run marketing program
POST	`/v1/notebook/generate`	Run notebook program
POST	`/v1/obsidian/analyze`	Run obsidian program
POST	`/v1/mcp/provision`	Run MCP program
POST	`/v1/artifacts/generate`	Run artifacts program
POST	`/v1/remotion/generate`	Run remotion program
POST	`/v1/canvas/generate`	Run canvas program
POST	`/v1/algorithmic/generate`	Run algorithmic program
POST	`/v1/agentic-purchasing/generate`	Run agentic purchasing program
GET	`/v1/programs`	List all programs with generator counts
GET	`/v1/projects/:id/generated-files/:path`	Download individual generated file
GET	`/v1/projects/:id/export`	Download ZIP of generated files

Billing & Account

Method	Path	Description
POST	`/v1/accounts`	Create account
GET	`/v1/account`	Get account info
POST	`/v1/account/keys`	Create API key
GET	`/v1/account/keys`	List API keys
POST	`/v1/account/keys/:id/revoke`	Revoke API key
GET	`/v1/account/usage`	Get usage stats
GET	`/v1/account/quota`	Get quota info
POST	`/v1/account/tier`	Update billing tier
POST	`/v1/account/programs`	Update program entitlements
POST	`/v1/account/github-token`	Save encrypted GitHub token
GET	`/v1/account/github-token`	List GitHub tokens
DELETE	`/v1/account/github-token/:token_id`	Delete GitHub token
GET	`/v1/billing/history`	Billing tier change audit trail
GET	`/v1/billing/proration`	Proration preview for tier changes

Funnel & Plans

Method	Path	Description
GET	`/v1/plans`	Get plan catalog
POST	`/v1/account/seats`	Invite team member
GET	`/v1/account/seats`	List team seats
POST	`/v1/account/seats/:id/revoke`	Revoke seat
GET	`/v1/account/upgrade-prompts`	Get contextual upgrade prompts
GET	`/v1/account/funnel-status`	Get funnel stage
GET	`/v1/admin/funnel-metrics`	Aggregate funnel analytics

Search & Versions

Method	Path	Description
POST	`/v1/search/index`	Index snapshot content for full-text search
POST	`/v1/search/query`	Full-text search across indexed content
GET	`/v1/search/:id/stats`	Search index statistics
GET	`/v1/snapshots/:id/versions`	List generation versions
GET	`/v1/snapshots/:id/versions/:num`	Get specific version with files
GET	`/v1/snapshots/:id/diff?old=N&new=M`	Diff between two versions

Webhooks

Method	Path	Description
POST	`/v1/account/webhooks`	Create webhook
GET	`/v1/account/webhooks`	List webhooks
DELETE	`/v1/account/webhooks/:id`	Delete webhook
POST	`/v1/account/webhooks/:id/toggle`	Toggle webhook active/disabled
GET	`/v1/account/webhooks/:id/deliveries`	List delivery attempts

Infrastructure

Method	Path	Description
GET	`/v1/health`	Health check
GET	`/v1/health/live`	Liveness probe
GET	`/v1/health/ready`	Readiness probe (DB connectivity)
GET	`/v1/metrics`	Prometheus-style metrics
GET	`/v1/db/stats`	Database statistics
POST	`/v1/db/maintenance`	Database maintenance (vacuum, WAL checkpoint)
GET	`/v1/docs`	OpenAPI 3.1 specification
GET	`/v1/admin/stats`	System-wide statistics
GET	`/v1/admin/accounts`	Admin: list all accounts
GET	`/v1/admin/activity`	Admin: recent activity feed

Input Methods

File Upload — POST /v1/snapshots with multipart body
GitHub URL — POST /v1/github/analyze with { "url": "https://github.com/..." }
CLI (local) — axis analyze <directory> scans local files
CLI (remote) — axis github <url> fetches from GitHub

Tech Stack

Runtime: Node.js 20+, TypeScript 5.7 strict
Backend: Zero-dependency custom HTTP router, Neon Postgres (pg, async pooled)
Frontend: Vite 6 + React 19, CSS design system (dark theme)
Testing: Vitest 4 — ~4,900 tests across ~190 files, run against Postgres 16
Benchmarks: Vitest bench harness (packages/repo-parser/src/perf.bench.ts, npx vitest bench) covers parseRepo at 200-file scale; no specific latency number is pinned here — this repo's own honesty policy (see packages/generator-core/src/perf-compliance.test.ts) bans citing a perf figure unless it's sourced from a checked-in, machine-generated results file, which doesn't yet exist for this bench. The 7 agentic-purchasing engines DO have one: packages/generator-core/perf-results.json (regenerate via pnpm bench:compliance).
Build: pnpm workspaces, tsc per package
CI: GitHub Actions (Node 20/22 matrix, coverage, dep audit, Docker build)

Development

bash

pnpm install          # Install all dependencies
pnpm build            # Build all packages + apps
pnpm test             # Run all tests
npx vitest run        # Run tests directly
npx vitest bench      # Run performance benchmarks
npx vitest --coverage # Run tests with coverage report

See CONTRIBUTING.md for how to add a generator, endpoint, or program.

Input methods

Method	How
GitHub URL	`POST /v1/github/analyze` with `{"url":"https://github.com/..."}`
File upload	`POST /v1/snapshots` multipart body
CLI (local)	`axis analyze <directory>`
CLI (remote)	`axis github <url>`
MCP	`tools/call` → `analyze_repo` or `analyze_files`

Website: https://iliad.trustfabric.ai · Live API: https://api.iliad.trustfabric.ai · Docs: https://api.iliad.trustfabric.ai/v1/docs · MCP: https://api.iliad.trustfabric.ai/mcp

License

Install

Tools (36)

analyze_repoanalyze_fileslist_programsget_snapshotget_artifactprepare_agentic_purchasing_previewprepare_agentic_purchasingcloser

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.iliad.trustfabric.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "axis-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.iliad.trustfabric.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.lastmanupinc-hub/axis-toolbox MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

analyze_repo

analyze_files

list_programs

get_snapshot

get_artifact

prepare_agentic_purchasing_preview

prepare_agentic_purchasing

closer

deploy

search_and_discover_tools

discover_commerce_tools

improve_my_agent_with_axis

discover_agentic_purchasing_needs

get_referral_code

get_referral_credits

iliad_web_research

iliad_web_research_crawl

iliad_object_storage

iliad_vector_database

iliad_embeddings

iliad_transactional_email

iliad_llm_inference

iliad_code_sandbox

iliad_document_parsing

iliad_web_search

iliad_text_to_speech

iliad_speech_to_text

iliad_analytics

iliad_hygiene

sca_exemption_decision

grade_compliance

assemble_ce3_evidence

build_ap2_mandate

score_dispute_readiness

assemble_representment

iliad_network_tokenization

Axis' Iliad

AXIS Ecosystem

Try it in 30 seconds — no signup required

What you get

Plus the begin loop — hand it to an agent and say begin

For AI agents — MCP integration

Pricing

Self-host

System Requirements

Quick Start

Docker

Architecture

Programs (21)

API Endpoints

Core Pipeline

Billing & Account

Funnel & Plans

Search & Versions

Webhooks

Infrastructure

Input Methods

Tech Stack

Development

Input methods

License

Install

Remote endpoint

Related servers

Plus the begin loop — hand it to an agent and say `begin`