get_health
Return public health and persistence state.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Catalog
Hugging Bay
Official100 toolsLiveby barneywohl
Search and verify open AI artifacts, hosted downloads, trust, and provenance.
Search and verify open AI artifacts, hosted downloads, trust, and provenance.
Captured live from the server via tools/list.
get_catalog_coverage
Return public catalog scale, source coverage, and readiness facts.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_open_source_radar
Return popular, newest, and non-Hugging Face open-source AI records in one bounded response.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_trending
Return public trending artifacts from aggregate pageview, download, mirror-request, and product-action signals.
Parameters2
| window | string | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"window": {
"type": "string",
"enum": [
"24h",
"7d",
"30d",
"all"
]
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 50
}
},
"additionalProperties": false
}get_traffic
Return privacy-safe aggregate traffic, hosted-download, mirror-request, product-action, and agent/crawler discovery signals.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_agent_discovery
Return the single-call agent discovery contract for answer engines, OpenClaw/Hermes-style agents, MCP clients, OpenAPI users, crawlers, citation targets, and bounded API entrypoints.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_ai_bot_allowlist
Return the machine-readable AI crawler/user-agent allowlist, official verification links, and WAF guidance.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_ai_search_guidance
Return citation-ready AI-search guidance for Perplexity, ChatGPT, Gemini, Grok, Claude, open agents, and MCP clients.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_agent_recommendation_kit
Return ready-to-use recommendation wording, assistant prompts, integration snippets, citation targets, sharing templates, and claim boundaries for AI assistants and agents.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_ai_mention_monitor
Return the AI answer-engine mention monitoring contract, prompt targets, provider targets, citation goals, and crawler readiness signals.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_ai_mention_results
Return public AI mention/citation result rows and summary rollups for answer-engine visibility monitoring.
Parameters3
| provider | string | optional | |
| promptId | string | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"provider": {
"type": "string"
},
"promptId": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"additionalProperties": false
}get_citation_pack
Return a compact citation pack for answer engines: safe claims, avoid claims, citation order, proof URLs, and bounded extraction rows.
Parameters3
| q | string | optional | |
| query | string | optional | |
| slug | string | optional |
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"query": {
"type": "string"
},
"slug": {
"type": "string"
}
},
"additionalProperties": false
}get_source_coverage
Return one provider's coverage, policy, rollups, and top imported records.
Parameters2
| id | string | optional | |
| source | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"source": {
"type": "string"
}
},
"additionalProperties": false
}get_recommendations
Return public mirror signals, totals, and pack summaries.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}recommend_artifacts
Return ranked artifact recommendations for a concrete use case, with fit reasons, tool commands, and hosted/mirror actions.
Parameters6
| useCase | string | optional | |
| q | string | optional | |
| tool | string | optional | |
| commercial | boolean | optional | |
| hosted | boolean | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"useCase": {
"type": "string"
},
"q": {
"type": "string"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
},
"commercial": {
"type": "boolean"
},
"hosted": {
"type": "boolean"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 25
}
},
"additionalProperties": false
}get_agent_tasks
Return intent-specific agent workflows for RAG, hosted downloads, commercial-safe search, and mirror prioritization.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_publisher_release_template
Return a copyable Hugging Bay release manifest template for labs, including source URLs, hashes, runtime notes, upload-session body, and reviewed fallback fields.
Parameters1
| kind | string | optional |
Raw schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"llm",
"dataset",
"vision",
"audio",
"agent",
"app",
"eval"
]
}
},
"additionalProperties": false
}list_publishers
List public publisher namespaces with artifact counts, hosted-file counts, claim state, and trust stats.
Parameters2
| q | string | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"additionalProperties": false
}get_publisher_profile
Fetch one public publisher namespace profile with releases, hosted files, claim state, and trust stats.
Parameters2
| namespace | string | required | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"namespace": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"required": [
"namespace"
],
"additionalProperties": false
}get_mirror_readiness
Return mirror candidates with readiness scores, blockers, compatible tools, and selected safe files.
Parameters5
| limit | number | optional | |
| candidateLimit | number | optional | |
| requestedOnly | boolean | optional | |
| tool | string | optional | |
| maxBytes | number | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 50
},
"candidateLimit": {
"type": "number",
"minimum": 1,
"maximum": 100
},
"requestedOnly": {
"type": "boolean"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
},
"maxBytes": {
"type": "number",
"minimum": 1
}
},
"additionalProperties": false
}get_mirror_scale_plan
Return a public mirror scaling readiness preview with candidate counts, storage readiness, policy, and blockers. Does not expose execution commands or mirror files.
Parameters7
| limit | number | optional | |
| candidateLimit | number | optional | |
| targetHostedFiles | number | optional | |
| maxPlannedBytes | number | optional | |
| requestedOnly | boolean | optional | |
| includeSupportOnly | boolean | optional | |
| includeReviewedRiskyWeights | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 25
},
"candidateLimit": {
"type": "number",
"minimum": 1,
"maximum": 50
},
"targetHostedFiles": {
"type": "number",
"minimum": 1
},
"maxPlannedBytes": {
"type": "number",
"minimum": 1
},
"requestedOnly": {
"type": "boolean"
},
"includeSupportOnly": {
"type": "boolean"
},
"includeReviewedRiskyWeights": {
"type": "boolean"
}
},
"additionalProperties": false
}list_stacks
List practical AI stack packs for high-intent use cases.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_stack
Fetch one stack pack with bounded ranked artifact rows.
Parameters1
| slug | string | required |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
],
"additionalProperties": false
}list_answer_packs
List citation-ready answer packs for AI search engines, agents, and common open AI artifact questions.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_answer_pack
Fetch one answer pack with short answer, canonical citations, extraction APIs, and ranked rows.
Parameters1
| slug | string | required |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
],
"additionalProperties": false
}get_ranking
Fetch one ranking as JSON so agents do not scrape ranking HTML.
Parameters1
| slug | string | required |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
],
"additionalProperties": false
}search_artifacts
Search bounded public catalog rows with summary=1, filters, limit, cursor, and optional semantic reranking.
Parameters15
| q | string | optional | |
| limit | number | optional | |
| cursor | string | optional | |
| sort | string | optional | |
| type | string | optional | |
| license | string | optional | |
| task | string | optional | |
| framework | string | optional | |
| format | string | optional | |
| hosting | string | optional | |
| reviewStatus | string | optional | |
| source | string | optional | |
| commercial | string | optional | |
| semantic | string | optional | |
| explain | string | optional |
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 200
},
"cursor": {
"type": "string"
},
"sort": {
"type": "string",
"enum": [
"best",
"ready",
"mirrorable",
"trust",
"updated",
"downloads",
"stars",
"demand",
"mirrors",
"name",
"size",
"license"
]
},
"type": {
"type": "string"
},
"license": {
"type": "string"
},
"task": {
"type": "string"
},
"framework": {
"type": "string"
},
"format": {
"type": "string"
},
"hosting": {
"type": "string"
},
"reviewStatus": {
"type": "string",
"enum": [
"first-review",
"needs-evidence",
"reviewed",
"verified-run",
"benchmark"
]
},
"source": {
"type": "string"
},
"commercial": {
"type": "string",
"enum": [
"1",
"true"
]
},
"semantic": {
"type": "string",
"enum": [
"1",
"true"
]
},
"explain": {
"type": "string",
"enum": [
"1",
"true"
]
}
},
"additionalProperties": false
}resolve_artifact
Resolve an upstream repo URL, owner/name, or artifact id to a Hugging Bay artifact plus hosted/download/mirror actions.
Parameters4
| repo | string | optional | |
| url | string | optional | |
| q | string | optional | |
| source | string | optional |
Raw schema
{
"type": "object",
"properties": {
"repo": {
"type": "string"
},
"url": {
"type": "string"
},
"q": {
"type": "string"
},
"source": {
"type": "string",
"enum": [
"huggingface",
"modelscope",
"github",
"zenodo",
"arxiv",
"openml",
"dataverse",
"datacite",
"paperswithcode",
"opendatalab",
"opencompass"
]
}
},
"additionalProperties": false
}get_artifact
Fetch one full artifact JSON document by id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}find_ungated_alternatives
For a gated or restricted model, return ranked ungated, commercially-usable equivalents at the same capability tier (with hosted-download availability). Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}will_it_fit
Will this model run on a given GPU? Returns per-GPU fit verdict (fits/tight/no), weights+KV-cache VRAM estimate, max context that fits, and smaller-quant options. Args: id, gpu (e.g. rtx4090-24, rtx3090-24, a100-80, h100-80, mac-m3-max-64), ctx, batch.
Parameters4
| id | string | required | |
| gpu | string | optional | |
| ctx | integer | optional | |
| batch | integer | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"gpu": {
"type": "string"
},
"ctx": {
"type": "integer"
},
"batch": {
"type": "integer"
}
},
"required": [
"id"
],
"additionalProperties": false
}recommend_safe_model
Recommend commercially-safe, ungated open models for a use case. Returns a ranked shortlist with license clarity and hosted-download availability. Args: task (e.g. coding, chat, embeddings, vision, reasoning), commercial (true to restrict to commercial-safe licenses), limit.
Parameters3
| task | string | optional | |
| commercial | boolean | optional | |
| limit | integer | optional |
Raw schema
{
"type": "object",
"properties": {
"task": {
"type": "string"
},
"commercial": {
"type": "boolean"
},
"limit": {
"type": "integer"
}
},
"additionalProperties": false
}get_quantizations
List available quantizations for a model (GGUF/AWQ/GPTQ/etc.) with per-quant size, precision, and hosted-download availability, so an agent can pick the smallest that fits. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_model_family
Model genealogy: exact base-model ancestor chain (with effective-license carry-through) plus known catalog derivatives that name this model as their base. Use to trace provenance or find fine-tunes/quants built on a model. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_card_doctor
Score a model card's completeness 0-100 (grade A-F) across summary, license clarity, base-model, eval results, datasets, tags, hosted bytes, and provenance, with a prioritized fix list. Use as a card-quality signal or to tell a publisher exactly what to add. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_model_report
One-call composite decision document for a model: safe-to-run verdict, license + effective-commercial-use, GPU fit summary, model-card completeness score, and base-model lineage — plus links to every detail endpoint. The fastest way to evaluate a model before recommending or running it. Args: id, gpu (optional, e.g. rtx4090-24).
Parameters2
| id | string | required | |
| gpu | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"gpu": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}find_and_verify_model_for_task
The golden path in one call: recommend open models for a task AND verify each finalist (safe-to-run verdict, effective license, GPU fit, card score, lineage). Returns ranked composite reports plus a bestPick. Use this FIRST when a user asks 'what model should I use for X'. Args: task (e.g. coding, chat, embeddings, vision), commercial (true to require commercial-safe licenses), gpu (e.g. rtx4090-24), limit (1-5).
Parameters4
| task | string | required | |
| commercial | boolean | optional | |
| gpu | string | optional | |
| limit | integer | optional |
Raw schema
{
"type": "object",
"properties": {
"task": {
"type": "string"
},
"commercial": {
"type": "boolean"
},
"gpu": {
"type": "string"
},
"limit": {
"type": "integer"
}
},
"required": [
"task"
],
"additionalProperties": false
}plan_local_deployment
One-call local-run plan for a model: GPU fit verdict, the recommended variant (as-is or the smallest hosted quant that fits), the full quant table, and ordered steps (safety check, hash-verified download plan, ollama/llama.cpp/vLLM run commands, post-download hash verify). Args: id, gpu, ctx.
Parameters3
| id | string | required | |
| gpu | string | optional | |
| ctx | integer | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"gpu": {
"type": "string"
},
"ctx": {
"type": "integer"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_leaderboard
Trust-weighted open-model leaderboard for a benchmark (verified evidence outranks self-reported scores); each row carries license clarity. Args: benchmark (e.g. mmlu, humaneval), metric (optional).
Parameters2
| benchmark | string | required | |
| metric | string | optional |
Raw schema
{
"type": "object",
"properties": {
"benchmark": {
"type": "string"
},
"metric": {
"type": "string"
}
},
"required": [
"benchmark"
],
"additionalProperties": false
}get_model_benchmarks
All normalized benchmark results recorded for one model (benchmark, metric, score, verified flag). Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}recommend_with_citation
Paste-ready recommendation PARAGRAPH with inline [n] citation markers resolving to stable Hugging Bay URLs — for when you need to answer 'what model should I use' in prose with checkable sources. Args: task, commercial, gpu.
Parameters3
| task | string | required | |
| commercial | boolean | optional | |
| gpu | string | optional |
Raw schema
{
"type": "object",
"properties": {
"task": {
"type": "string"
},
"commercial": {
"type": "boolean"
},
"gpu": {
"type": "string"
}
},
"required": [
"task"
],
"additionalProperties": false
}get_integration_snippets
Copy-paste-runnable integration snippets for a model across huggingface-cli/huggingface_hub/transformers/ollama/llama.cpp/vLLM/LangChain/LlamaIndex plus a hash-verify recipe and MCP config — filtered to what actually applies to the artifact's type and formats. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}inspect_model_binary
Byte-level inspection of a model's hosted files: parses the safetensors header (real param count, dtypes), GGUF header (architecture, context, quant), and config.json (custom-code architecture risk), then cross-checks the bytes against the declared card. Catches mislabeled sizes and card/weights mismatches. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_runtime_compat
Which local runners can run this exact model (by format + platform) with the run command for each, plus incompatible runners and why. Args: id, platform.
Parameters2
| id | string | required | |
| platform | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"platform": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_impact_graph
Dependency blast radius for a model: known catalog derivatives affected if it changes/withdraws + the base-model chain it inherits. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_change_timeline
Typed change timeline for a model: identity/digest changes and advisories, newest first (distinguishes changed vs unsafe). Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}delegate_a2a_task
Delegate find+verify+plan for a task to Hugging Bay; get back a SIGNED decision (best eligible model, budget check, alternatives, next actions). Verify the signature to trust it. Args: task, constraints{gpu, commercial, maxBytes}.
Parameters2
| task | string | required | |
| constraints | object | optional |
Raw schema
{
"type": "object",
"properties": {
"task": {
"type": "string"
},
"constraints": {
"type": "object"
}
},
"required": [
"task"
],
"additionalProperties": false
}check_agent_action
Policy gate for an agent action: does downloading/using this model fit size/license/destination/safety budgets? Returns allow|deny + reasons. Args: artifactId, action, maxBytes, requireCommercial.
Parameters4
| artifactId | string | required | |
| action | string | optional | |
| maxBytes | integer | optional | |
| requireCommercial | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"artifactId": {
"type": "string"
},
"action": {
"type": "string"
},
"maxBytes": {
"type": "integer"
},
"requireCommercial": {
"type": "boolean"
}
},
"required": [
"artifactId"
],
"additionalProperties": false
}get_release_preflight
Publisher preflight for a release: objective integrity BLOCKERS (unhashed files, no license, no inventory) separated from documentation-quality WARNINGS (never blocking, never a safety signal). Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_model_sbom
Standards-backed SBOM for a model: SPDX 2.3 (default), CycloneDX 1.5, or SPDX tag:value — hashed files, license (SPDX id), and base-model relationships, for tools you already run. Args: id, format (spdx|cyclonedx|spdx-tag).
Parameters2
| id | string | required | |
| format | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"format": {
"type": "string",
"enum": [
"spdx",
"cyclonedx",
"spdx-tag"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}get_model_bom
Signed, CycloneDX-compatible AI Bill of Materials for a model: weights files with SHA-256 hashes, license posture with effective commercial-use, base-model dependency chain, and scan/verification state. Archive it or diff it across versions for supply-chain audits. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_stack_blueprint
Executable open-model stack for a job (laptop-rag, local-coding, multilingual-embeddings, tool-calling-agent, document-extraction): each role resolved to an exact eligible verified variant with lock + run steps. Args: slug, gpu, commercial.
Parameters3
| slug | string | required | |
| gpu | string | optional | |
| commercial | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"gpu": {
"type": "string"
},
"commercial": {
"type": "boolean"
}
},
"required": [
"slug"
],
"additionalProperties": false
}plan_open_migration
Migrate off a closed model/API: given a closed model name (gpt-4o, text-embedding-3, whisper, ...), return eligible open alternatives + a migration plan with rollback. Args: from, gpu, commercial.
Parameters3
| from | string | required | |
| gpu | string | optional | |
| commercial | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"from": {
"type": "string"
},
"gpu": {
"type": "string"
},
"commercial": {
"type": "boolean"
}
},
"required": [
"from"
],
"additionalProperties": false
}diagnose_run_failure
Model Doctor: paste a failing run's log/error output and get a curated diagnosis — failure class, ranked non-destructive fixes, smaller hosted alternatives when memory-bound, and the model's chat contract when relevant. Args: log (required), runner, gpu, artifactId.
Parameters4
| log | string | required | |
| runner | string | optional | |
| gpu | string | optional | |
| artifactId | string | optional |
Raw schema
{
"type": "object",
"properties": {
"log": {
"type": "string"
},
"runner": {
"type": "string"
},
"gpu": {
"type": "string"
},
"artifactId": {
"type": "string"
}
},
"required": [
"log"
],
"additionalProperties": false
}get_chat_contract
Chat-template contract for a model: BOS/EOS/stop tokens, thinking markers, tool-calling conventions, and deterministic conformance fixtures — prevents correct weights from producing broken conversations. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}resolve_hb_uri
Resolve an immutable hb://{owner}/{name}@sha256:{digest} artifact identity. Returns 'resolved' when current bytes match, or an explicit 'identity-changed' warning — never silently retargets. Arg: uri.
Parameters1
| uri | string | required |
Raw schema
{
"type": "object",
"properties": {
"uri": {
"type": "string"
}
},
"required": [
"uri"
],
"additionalProperties": false
}get_bay_lock
Generate a bay.lock reproducible dependency document for an artifact: immutable hb:// identity, per-file sha256 + sizes + hosting, license verdict, safety snapshot. Restore/verify with the hbay CLI. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_license_risk
Whole-tree license risk for a model: risk grade (low|moderate|elevated|high), effective commercial-use across the base-model chain, laundering signal, and the combined obligations checklist. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}check_typosquat
Impersonation check: is this repo a near-miss (edit distance) of a popular publisher or model name? Catches 'Qwem/Qwen2.5'-style supply-chain lookalikes. Verdict: clear | lookalike-naming | suspected-impersonation. Arg: id.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}diff_manifests
File-level integrity diff between two artifacts' manifests (added/removed/changed-hash files) — a supply-chain tamper check for re-mirrors or version bumps. A changed sha256 on a same-named file is a red flag. Args: id, against (the other artifact id).
Parameters2
| id | string | required | |
| against | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"against": {
"type": "string"
}
},
"required": [
"id",
"against"
],
"additionalProperties": false
}get_security_advisories
Public security advisories: flagged and quarantined artifacts, open moderation cases, and the scanning policy.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}list_revocations
List revoked artifact identities (withdrawn/compromised/license-revoked/superseded/malware). Honor these before running or trusting an artifact; a match means do not run.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}check_revocation
Check whether a specific artifact identity is revoked. Returns revoked true/false plus reason, severity, and a replacement id when one exists.
Parameters1
| id | string | required | Artifact id to check. |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Artifact id to check."
}
},
"required": [
"id"
],
"additionalProperties": false
}scan_artifact_threats
Adversarial-pattern scan of one artifact: unsafe serialization (pickle), payloads hidden among weights, license laundering, homoglyph/typosquat namespaces, metadata spoofing. Returns verdict clean|suspicious|dangerous with per-threat evidence — a verify-before-trust signal, not proof of malice.
Parameters1
| id | string | required | Artifact id to scan. |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Artifact id to scan."
}
},
"required": [
"id"
],
"additionalProperties": false
}get_bundle_state
Runnable-completeness verdict for one artifact: indexed|metadata-complete|partial-hosted|complete-hosted|run-verified|revoked with the exact missing components. Use before pulling — file counts never imply runnability.
Parameters1
| id | string | required | Artifact id. |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Artifact id."
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_passport
Signed, digest-specific artifact passport: provenance, license verdict, safety, bundle state, evidence counts — plus ready-to-paste README embed snippets. Tamper-evident; a changed manifestDigest means the bytes changed.
Parameters1
| id | string | required | Artifact id. |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Artifact id."
}
},
"required": [
"id"
],
"additionalProperties": false
}get_community_blueprints
Moderator-approved community executable stacks (reviewed queue: sha256-pinned dependencies, allowlisted commands; nothing publishes without review).
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_eval_suites
Fixed BYOC eval suites for try-before-pull on compute the user owns. Pass suite + endpointKind (openai-compatible|ollama|llama-cpp) + model for an executable request plan — credentials never touch the server.
Parameters3
| suite | string | optional | |
| endpointKind | string | optional | |
| model | string | optional |
Raw schema
{
"type": "object",
"properties": {
"suite": {
"type": "string"
},
"endpointKind": {
"type": "string"
},
"model": {
"type": "string"
}
},
"additionalProperties": false
}get_bundles_summary
Public bundle-state counts: weightsHosted vs supportFilesOnly vs metadataOnly — hosting reported by runnable completeness, never file counts.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_incidents
Declared service incidents: open incidents plus incidents resolved within 90 days. Complements the live health/readiness probes.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_verification_missions
Evidence missions: ranked verification gaps in the most-used artifacts (first verified run, license pin-down), each with exact submit instructions. Use to direct verification effort where one receipt most improves the evidence base.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}check_artifact_safety
One decisive safe-to-run verdict: pass an artifact id, a repo (owner/name), or a raw file sha256 — unknown hashes return verdict unknown so unverified provenance reads as a risk signal.
Parameters3
| id | string | optional | |
| repo | string | optional | |
| sha256 | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"repo": {
"type": "string"
},
"sha256": {
"type": "string"
}
},
"additionalProperties": false
}get_artifact_metadata
Fetch agent-oriented artifact metadata with provenance, hosting, and safe next steps.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_bundle
Fetch one artifact's metadata, card, trust bundle, hosted files, and mirror readiness in one response.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_release_bundle
Fetch a launch-ready release bundle for labs and agents: publisher claim, same-as-upstream evidence, trust bundle, hosted files, local-run commands, and reviewed fallback readiness.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_release_readiness
Fetch a compact release readiness score/checklist for a lab release: namespace, provenance, license, scans, signed manifests, hosted files, runtime guidance, community proof, and reviewed fallback status.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_distribution
Fetch one artifact's hosted download state, upstream source, and reviewed peer-assisted fallback metadata.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_peer_fallbacks
Fetch one artifact's reviewed torrent/magnet fallback bundle, scoped to hosted-file hashes and reviewer evidence.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_insights
Fetch one artifact's fit labels, trust gaps, evidence, hardware fit, and mirror decision data.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_local_kit
Fetch copyable local-use commands, required files, warnings, and next actions for one artifact.
Parameters2
| id | string | required | |
| tool | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}get_download_plan
Fetch a manifest-backed plan for downloading all Hugging Bay-hosted verified files for one artifact.
Parameters2
| id | string | required | |
| tool | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_card
Fetch repo-grade artifact card JSON or Markdown.
Parameters2
| id | string | required | |
| markdown | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"markdown": {
"type": "boolean"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_artifact_reviews
Fetch public community ratings, reviews, and verified-run attestations for an artifact.
Parameters2
| id | string | required | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 200
}
},
"required": [
"id"
],
"additionalProperties": false
}get_community_signals
Fetch aggregate public community trust signals, recent reviews, and top helpful reviews.
Parameters1
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"additionalProperties": false
}get_review_queue
Fetch high-priority artifacts that need community reviews, verified-run evidence, or benchmark reports.
Parameters4
| mode | string | optional | |
| hosting | string | optional | |
| maxReviews | number | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"first-review",
"needs-evidence",
"verified-run",
"benchmark"
]
},
"hosting": {
"type": "string",
"enum": [
"actionable",
"hosted",
"reviewable",
"all"
]
},
"maxReviews": {
"type": "number",
"minimum": 0,
"maximum": 25
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"additionalProperties": false
}get_evidence_rollups
Fetch public benchmark/evidence rollups grouped by benchmark, tool, and hardware.
Parameters1
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
}
},
"additionalProperties": false
}compare_artifacts
Compare up to six artifact ids or owner/name repos side by side.
Parameters1
| ids | array | required |
Raw schema
{
"type": "object",
"properties": {
"ids": {
"type": "array",
"minItems": 1,
"maxItems": 6,
"items": {
"type": "string"
}
}
},
"required": [
"ids"
],
"additionalProperties": false
}preview_file
Preview one hosted text-like file with a bounded first chunk and row samples.
Parameters2
| id | string | required | |
| path | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"path": {
"type": "string"
}
},
"required": [
"id",
"path"
],
"additionalProperties": false
}list_files
List one artifact's files with bounded pagination.
Parameters4
| id | string | required | |
| limit | number | optional | |
| cursor | string | optional | |
| tool | string | optional |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 500
},
"cursor": {
"type": "string"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}list_downloadable_files
List files actually hosted by Hugging Bay.
Parameters7
| q | string | optional | |
| pack | string | optional | |
| artifactId | string | optional | |
| path | string | optional | |
| sourceKind | string | optional | |
| tool | string | optional | |
| limit | number | optional |
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"pack": {
"type": "string"
},
"artifactId": {
"type": "string"
},
"path": {
"type": "string"
},
"sourceKind": {
"type": "string"
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 1000
}
},
"additionalProperties": false
}list_mirror_packs
List curated discovery/download packs.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_mirror_pack
Fetch one curated pack with artifact rows.
Parameters1
| slug | string | required |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
],
"additionalProperties": false
}list_mirror_demand
List requested and high-download mirror candidates.
Parameters3
| limit | number | optional | |
| requestedOnly | boolean | optional | |
| requested | boolean | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
},
"requestedOnly": {
"type": "boolean"
},
"requested": {
"type": "boolean"
}
},
"additionalProperties": false
}list_mirrors
List registered Hugging Bay mirror nodes and health state.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}list_topics
List generated catalog topics.
Parameters2
| limit | number | optional | |
| cursor | string | optional |
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"minimum": 1,
"maximum": 100
},
"cursor": {
"type": "string"
}
},
"additionalProperties": false
}get_topic
Fetch one topic and ranked artifact rows.
Parameters1
| slug | string | required |
Raw schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
],
"additionalProperties": false
}get_trust_bundle
Fetch artifact trust evidence.
Parameters1
| id | string | required |
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}get_manifest_signing_key
Fetch public manifest signing key metadata.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}get_indexing_status
Fetch sitemap, URL batch, and crawl-readiness status.
Parameters
No parameters.
Raw schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}list_indexing_urls
Fetch bounded canonical URL batches by kind, with optional artifact source/type/tool filters.
Parameters15
| kind | string | optional | |
| limit | number | optional | |
| cursor | string | optional | |
| q | string | optional | |
| source | string | optional | |
| type | string | optional | |
| license | string | optional | |
| format | string | optional | |
| hosting | string | optional | |
| reviewStatus | string | optional | |
| tool | string | optional | |
| worksWith | string | optional | |
| commercial | boolean | optional | |
| verified | boolean | optional | |
| sort | string | optional |
Raw schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"static",
"publisher",
"ranking",
"stack",
"intent",
"answer",
"citation-pack",
"source",
"topic",
"artifact",
"artifact-section",
"artifact-evidence",
"downloadable",
"agent-doc"
]
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 1000
},
"cursor": {
"type": "string"
},
"q": {
"type": "string"
},
"source": {
"type": "string"
},
"type": {
"type": "string"
},
"license": {
"type": "string"
},
"format": {
"type": "string"
},
"hosting": {
"type": "string"
},
"reviewStatus": {
"type": "string",
"enum": [
"first-review",
"needs-evidence",
"reviewed",
"verified-run",
"benchmark"
]
},
"tool": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
},
"worksWith": {
"type": "string",
"enum": [
"ollama",
"lm-studio",
"comfyui",
"transformers",
"llama.cpp"
]
},
"commercial": {
"type": "boolean"
},
"verified": {
"type": "boolean"
},
"sort": {
"type": "string",
"enum": [
"best",
"ready",
"mirrorable",
"trust",
"downloads",
"stars",
"mirrors",
"demand",
"name",
"size",
"license",
"updated"
]
}
},
"additionalProperties": false
}README not available yet.
Install
Tools (100)
get_healthget_catalog_coverageget_open_source_radarget_trendingget_trafficget_agent_discoveryget_ai_bot_allowlistget_ai_search_guidance
claude_desktop_config.json
{
"mcpServers": {
"hugging-bay": {
"command": "npx",
"args": [
"-y",
"hugging-bay-mcp@0.1.0"
]
}
}
}