ToolRouter

Official48 tools

by Humanleap · TypeScript

The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.

Humanleap ToolRouter MCP Server

ToolRouter (io.github.Humanleap/toolrouter) provides an MCP connection that routes an AI agent to a hosted tools catalog. With a single connection, agents can discover and call specialist tools through the hosted gateway, with free tools available immediately and paid tools charged per call. ToolRouter advertises 47 tools and targets “model-context-protocol” environments.

🛠️ Key Features

MCP-based tool routing (“One MCP connection gives any AI agent 250+ hosted tools”)
Hosted gateway execution only (“Everything runs on the hosted gateway; nothing executes locally”)
Free tools available immediately; paid tools pay per call
Catalog routing described as a compact routing surface (~9,000 tokens of context)

🚀 Use Cases

Enable agents to call hosted capabilities such as web search and scraping
Tool categories referenced: image and video generation, SEO, finance, property, compliance

⚡ Developer Benefits

Centralized tool access via one MCP connection
Agent tool discovery and invocation through the ToolRouter catalog
Reduced context overhead for the routing catalog

⚠️ Limitations

Execution is not local; all operations run on the hosted gateway
Paid tools incur per-call charges

Topics

ai-toolsclaudemcpmcp-servermodel-context-protocolgemini-cli-extensionai-agentstool-routeropenrouter-for-tools

Captured live from the server via tools/list.

account_setup

Initialize or re-check your account, provision it when needed, and return your user ID and plan. CALL THIS FIRST when the user asks to set up ToolRouter, connect their account, check their account status, or get started.

Parameters

No parameters.

Raw schema

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

account_list

List all billing contexts (personal + teams) or get detail on one. No slug → summary list. With slug → full detail including team members, role, subscription status, and pointers to the team's connectors, credentials, keys, and files.

Parameters1

slug

string

optional

Account slug for detail view. Omit to list all.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Account slug for detail view. Omit to list all."
    }
  }
}

account_switch

Set the active billing context. Accepts a slug (e.g. "personal", "team:nd7fx…") or team ID.

Parameters1

context

string

required

Account slug or team ID to switch to (e.g. "personal", "team:nd7fx…").

Raw schema

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Account slug or team ID to switch to (e.g. \"personal\", \"team:nd7fx…\")."
    }
  },
  "required": [
    "context"
  ]
}

account_preferences

Read or write billing preferences (auto-reload, budget cap, default context). Pass action: "get" to read, action: "set" with fields to write.

Parameters6

action	string	required	"get" to read preferences, "set" to update them.
default_billing_context	string	optional	Default account to bill (set only). "personal" or "team:<id>".
auto_reload_enabled	boolean	optional	Enable or disable auto-reload (set only).
auto_reload_threshold	number	optional	Balance threshold (USD) that triggers a reload (set only).
auto_reload_amount	number	optional	Amount (USD) to reload when triggered (set only, max 500).
budget_limit	number \| null	optional	Monthly spending cap in USD, or null to remove (set only).

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "set"
      ],
      "description": "\"get\" to read preferences, \"set\" to update them."
    },
    "default_billing_context": {
      "type": "string",
      "description": "Default account to bill (set only). \"personal\" or \"team:<id>\"."
    },
    "auto_reload_enabled": {
      "type": "boolean",
      "description": "Enable or disable auto-reload (set only)."
    },
    "auto_reload_threshold": {
      "type": "number",
      "description": "Balance threshold (USD) that triggers a reload (set only).",
      "minimum": 0
    },
    "auto_reload_amount": {
      "type": "number",
      "description": "Amount (USD) to reload when triggered (set only, max 500).",
      "minimum": 1,
      "maximum": 500
    },
    "budget_limit": {
      "type": [
        "number",
        "null"
      ],
      "description": "Monthly spending cap in USD, or null to remove (set only).",
      "minimum": 0
    }
  },
  "required": [
    "action"
  ]
}

credits_balance

Current balance, plan tier, rate limits, and any negative-balance warnings for the active context.

Parameters

No parameters.

Raw schema

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

credits_usage

Usage summary or history. Pass scope: "me" | "team" and detail: "tool" | "skill". Sorted by cost with _others rollup.

Parameters5

scope	string	optional	Whose usage to show. "me" for personal, "team" for team-wide.
detail	string	optional	Detail level. "tool" groups by tool, "skill" adds per-skill breakdown.
period	string	optional	Time period to summarize. 'all' covers the last 30 days (the maximum window).
limit	number	optional	Number of top tools/skills to return. Remaining rolled into "_others". Default 10.
offset	number	optional	Records to skip for pagination (history mode). Default 0.

Raw schema

{
  "type": "object",
  "properties": {
    "scope": {
      "type": "string",
      "enum": [
        "me",
        "team"
      ],
      "description": "Whose usage to show. \"me\" for personal, \"team\" for team-wide."
    },
    "detail": {
      "type": "string",
      "enum": [
        "tool",
        "skill"
      ],
      "description": "Detail level. \"tool\" groups by tool, \"skill\" adds per-skill breakdown.",
      "default": "tool"
    },
    "period": {
      "type": "string",
      "enum": [
        "day",
        "week",
        "month",
        "all"
      ],
      "description": "Time period to summarize. 'all' covers the last 30 days (the maximum window).",
      "default": "all"
    },
    "limit": {
      "type": "number",
      "description": "Number of top tools/skills to return. Remaining rolled into \"_others\". Default 10.",
      "minimum": 0,
      "maximum": 500
    },
    "offset": {
      "type": "number",
      "description": "Records to skip for pagination (history mode). Default 0.",
      "minimum": 0
    }
  }
}

subscription_manage

Get a Stripe management URL (portal, upgrade, or cancel). Also covers billing portal — returns the URL for the user to open.

Parameters2

action	string	required	"subscribe" to start a subscription, "manage" to view/cancel existing subscription.
tier	string	optional	Which plan to subscribe to (required for "subscribe" action).

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "subscribe",
        "manage"
      ],
      "description": "\"subscribe\" to start a subscription, \"manage\" to view/cancel existing subscription."
    },
    "tier": {
      "type": "string",
      "enum": [
        "lite",
        "plus"
      ],
      "description": "Which plan to subscribe to (required for \"subscribe\" action)."
    }
  },
  "required": [
    "action"
  ]
}

invoice_list

List invoices for the active billing context.

Parameters1

limit

number

optional

Number of invoices to return (default 10, max 20).

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Number of invoices to return (default 10, max 20).",
      "minimum": 1,
      "maximum": 20
    }
  }
}

key_list

List API keys (summary) or get detail on one key. Pass key_id for detail view.

Parameters1

key_id

string

optional

Key ID for detail view. Omit to list all.

Raw schema

{
  "type": "object",
  "properties": {
    "key_id": {
      "type": "string",
      "description": "Key ID for detail view. Omit to list all."
    }
  }
}

key_create

Create a new API key. Returns the secret once — save it immediately.

Parameters1

name

string

required

A name to identify this key (e.g. "Claude Desktop", "Production Bot").

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "A name to identify this key (e.g. \"Claude Desktop\", \"Production Bot\")."
    }
  },
  "required": [
    "name"
  ]
}

key_delete

Revoke an API key. Refuses to revoke the currently-authenticating key.

Parameters1

key_id

string

required

The key ID to revoke (from key_list).

Raw schema

{
  "type": "object",
  "properties": {
    "key_id": {
      "type": "string",
      "description": "The key ID to revoke (from key_list)."
    }
  },
  "required": [
    "key_id"
  ]
}

credential_list

List saved credentials (summary) or detail on one. Pass name for detail view. Pass show_available: true to include the full credential catalog.

Parameters3

name	string	optional	Credential name for detail view. Omit to list all saved.
context	string	optional	"personal" or "team:<id>". Defaults to personal.
show_available	boolean	optional	Include the full catalogue of available BYOK options. Default false.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Credential name for detail view. Omit to list all saved."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" or \"team:<id>\". Defaults to personal."
    },
    "show_available": {
      "type": "boolean",
      "description": "Include the full catalogue of available BYOK options. Default false."
    }
  }
}

credential_save

Save a credential (BYOK provider API key). Saved keys persist across sessions and are used automatically.

Parameters5

name	string	required	Credential name from the tool requirements (e.g. "ios_app_id", "openai").
value	string	required	The credential value to save.
label	string	optional	Human-readable label to identify this value (e.g. "MyApp", "Staging"). Required when saving multiple values for the same credential.
is_default	boolean	optional	Set this value as the default for this credential.
context	string	optional	"personal" or "team:<id>". Defaults to personal.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Credential name from the tool requirements (e.g. \"ios_app_id\", \"openai\")."
    },
    "value": {
      "type": "string",
      "description": "The credential value to save."
    },
    "label": {
      "type": "string",
      "description": "Human-readable label to identify this value (e.g. \"MyApp\", \"Staging\"). Required when saving multiple values for the same credential."
    },
    "is_default": {
      "type": "boolean",
      "description": "Set this value as the default for this credential."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" or \"team:<id>\". Defaults to personal."
    }
  },
  "required": [
    "name",
    "value"
  ]
}

credential_delete

Remove a saved credential. If label is provided, removes only that specific entry. If no label, removes ALL entries for that credential name.

Parameters3

name	string	required	Credential name to delete (e.g. "ios_app_id").
label	string	optional	Label of the specific entry to delete. Omit to remove all entries for this credential name.
context	string	optional	"personal" or "team:<id>". Defaults to personal.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Credential name to delete (e.g. \"ios_app_id\")."
    },
    "label": {
      "type": "string",
      "description": "Label of the specific entry to delete. Omit to remove all entries for this credential name."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" or \"team:<id>\". Defaults to personal."
    }
  },
  "required": [
    "name"
  ]
}

credential_default

Set the default value for a multi-value credential.

Parameters3

name	string	required	Credential name (e.g. "ios_app_id").
label	string	required	Label of the entry to make default (e.g. "Production").
context	string	optional	"personal" or "team:<id>". Defaults to personal.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Credential name (e.g. \"ios_app_id\")."
    },
    "label": {
      "type": "string",
      "description": "Label of the entry to make default (e.g. \"Production\")."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" or \"team:<id>\". Defaults to personal."
    }
  },
  "required": [
    "name",
    "label"
  ]
}

credential_guide

Get setup instructions for a specific credential.

Parameters1

name

string

required

Credential name (e.g. "ios_app_id", "play_store_app_id", "domain").

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Credential name (e.g. \"ios_app_id\", \"play_store_app_id\", \"domain\")."
    }
  },
  "required": [
    "name"
  ]
}

file_list

List or search files. Optional query triggers semantic search. Supports section, tags, plan_status, limit, cursor filters.

Parameters8

query	string	optional	Natural language search query. Omit to browse.
context	string	optional	"personal" (default) or "team:<id>".
section	string	optional	Filter by section. Omit to list all.
tags	array	optional	Filter to files matching ALL of these tags.
plan_status	string	optional	Filter plans by status.
prompt_type	string	optional	Filter prompts by type (only valid when section is "prompts").
limit	number	optional	Max results (default 20, max 50).
cursor	string	optional	Pagination cursor from a previous file_list response.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural language search query. Omit to browse."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    },
    "section": {
      "type": "string",
      "enum": [
        "personas",
        "plans",
        "style_references",
        "assets",
        "products",
        "outfits",
        "scenes",
        "prompts",
        "storyboards"
      ],
      "description": "Filter by section. Omit to list all."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Filter to files matching ALL of these tags."
    },
    "plan_status": {
      "type": "string",
      "enum": [
        "draft",
        "active",
        "completed",
        "archived"
      ],
      "description": "Filter plans by status."
    },
    "prompt_type": {
      "type": "string",
      "enum": [
        "system",
        "user",
        "example",
        "template",
        "script"
      ],
      "description": "Filter prompts by type (only valid when section is \"prompts\")."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 20, max 50).",
      "default": 20
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor from a previous file_list response."
    }
  }
}

file_read

Read a file's full content. Text files return content inline. Binary files (images, video) return a download URL.

Parameters1

file_id

string

required

The file ID (e.g. "ast_a1b2c3d4e5f67890").

Raw schema

{
  "type": "object",
  "properties": {
    "file_id": {
      "type": "string",
      "description": "The file ID (e.g. \"ast_a1b2c3d4e5f67890\")."
    }
  },
  "required": [
    "file_id"
  ]
}

file_write

Create or update a file. Pass mode: "create" | "update". Binary uploads: call with binary: true to get an upload_url, then PUT bytes, then call with mode: "finalize".

Parameters16

mode	string	required	"create" for new files, "update" to edit existing, "finalize" to complete a binary upload.
file_id	string	optional	File ID to update (required for update/finalize).
name	string	optional	File name (required for create, max 200 chars).
section	string	optional	Which section to file under (required for create).
context	string	optional	"personal" (default) or "team:<id>".
content	string	optional	Text content (for .md files).
file_data	string	optional	Base64-encoded binary data (for images, video).
content_type	string	optional	MIME type. Defaults to "text/markdown" for content, "image/png" for file_data.
description	string	optional	Optional summary (max 500 chars).
tags	array	optional	Tags for organization (max 10).
plan_status	string	optional	Plan status (only for plans section).
prompt_meta	object	optional	Prompt metadata (only for prompts section).
image_data	string	optional	Base64-encoded image. Alternative to image_url when the bytes are already local.
image_url	string	optional	Public URL to download and host permanently.
asset_id	string	optional	Existing asset ID to retrieve URL without re-uploading.
filename	string	optional	Optional filename for the asset.

Raw schema

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "create",
        "update",
        "finalize"
      ],
      "description": "\"create\" for new files, \"update\" to edit existing, \"finalize\" to complete a binary upload."
    },
    "file_id": {
      "type": "string",
      "description": "File ID to update (required for update/finalize)."
    },
    "name": {
      "type": "string",
      "description": "File name (required for create, max 200 chars)."
    },
    "section": {
      "type": "string",
      "enum": [
        "personas",
        "plans",
        "style_references",
        "assets",
        "products",
        "outfits",
        "scenes",
        "prompts",
        "storyboards"
      ],
      "description": "Which section to file under (required for create)."
    },
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    },
    "content": {
      "type": "string",
      "description": "Text content (for .md files)."
    },
    "file_data": {
      "type": "string",
      "description": "Base64-encoded binary data (for images, video)."
    },
    "content_type": {
      "type": "string",
      "description": "MIME type. Defaults to \"text/markdown\" for content, \"image/png\" for file_data."
    },
    "description": {
      "type": "string",
      "description": "Optional summary (max 500 chars)."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tags for organization (max 10)."
    },
    "plan_status": {
      "type": "string",
      "enum": [
        "draft",
        "active",
        "completed",
        "archived"
      ],
      "description": "Plan status (only for plans section)."
    },
    "prompt_meta": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "system",
            "user",
            "example",
            "template",
            "script"
          ]
        }
      },
      "description": "Prompt metadata (only for prompts section)."
    },
    "image_data": {
      "type": "string",
      "description": "Base64-encoded image. Alternative to image_url when the bytes are already local."
    },
    "image_url": {
      "type": "string",
      "description": "Public URL to download and host permanently."
    },
    "asset_id": {
      "type": "string",
      "description": "Existing asset ID to retrieve URL without re-uploading."
    },
    "filename": {
      "type": "string",
      "description": "Optional filename for the asset."
    }
  },
  "required": [
    "mode"
  ]
}

file_delete

Delete a file. Cannot be undone. For team files: requires owner/admin role.

Parameters1

file_id

string

required

The file ID to delete.

Raw schema

{
  "type": "object",
  "properties": {
    "file_id": {
      "type": "string",
      "description": "The file ID to delete."
    }
  },
  "required": [
    "file_id"
  ]
}

persona_list

List your personas.

Parameters1

context

string

optional

"personal" (default) or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    }
  }
}

scene_list

List your scenes.

Parameters1

context

string

optional

"personal" (default) or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    }
  }
}

product_list

List your products.

Parameters1

context

string

optional

"personal" (default) or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    }
  }
}

outfit_list

List your outfits.

Parameters1

context

string

optional

"personal" (default) or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "\"personal\" (default) or \"team:<id>\"."
    }
  }
}

connector_list

List connected accounts and MCP servers (summary) or detail on one connector. Pass slug for detail including every tool the connector exposes. Optional type: "oauth" | "mcp" filter. Pass include_available: true to also see available catalog MCPs you can connect.

Parameters4

slug	string	optional	Connector slug for detail view. Omit to list all.
type	string	optional	Filter by connector type.
context	string	optional	Scope: "personal" (default) or "team:<id>" for a team.
include_available	boolean	optional	When true, also include catalog MCPs you have not connected yet.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Connector slug for detail view. Omit to list all."
    },
    "type": {
      "type": "string",
      "enum": [
        "oauth",
        "mcp"
      ],
      "description": "Filter by connector type."
    },
    "context": {
      "type": "string",
      "description": "Scope: \"personal\" (default) or \"team:<id>\" for a team."
    },
    "include_available": {
      "type": "boolean",
      "description": "When true, also include catalog MCPs you have not connected yet."
    }
  }
}

connector_add

Connect a new OAuth account or MCP server. For OAuth: pass type: "oauth", kind: "slack". For MCP catalog: pass catalog_slug. For custom MCP: pass url + auth_type.

Parameters10

type	string	optional	Type of connector to add.
kind	string	optional	OAuth connector kind (e.g. "slack", "notion"). Required for type: "oauth".
catalog_slug	string	optional	MCP catalog slug for one-click connect.
slug	string	optional	Short identifier for the connection.
display_name	string	optional	Human-readable name (custom MCP).
url	string	optional	MCP server endpoint URL (custom MCP).
auth_type	string	optional	Auth type (custom MCP). Default: none.
auth_token	string	optional	Auth token or API key.
header_name	string	optional	Custom header name (for header_key auth).
billing	string	optional	Scope: "personal" (default), "team" (auto-resolves), a team slug, or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "oauth",
        "mcp"
      ],
      "description": "Type of connector to add."
    },
    "kind": {
      "type": "string",
      "description": "OAuth connector kind (e.g. \"slack\", \"notion\"). Required for type: \"oauth\"."
    },
    "catalog_slug": {
      "type": "string",
      "description": "MCP catalog slug for one-click connect."
    },
    "slug": {
      "type": "string",
      "description": "Short identifier for the connection."
    },
    "display_name": {
      "type": "string",
      "description": "Human-readable name (custom MCP)."
    },
    "url": {
      "type": "string",
      "description": "MCP server endpoint URL (custom MCP)."
    },
    "auth_type": {
      "type": "string",
      "enum": [
        "none",
        "bearer",
        "header_key"
      ],
      "description": "Auth type (custom MCP). Default: none."
    },
    "auth_token": {
      "type": "string",
      "description": "Auth token or API key."
    },
    "header_name": {
      "type": "string",
      "description": "Custom header name (for header_key auth)."
    },
    "billing": {
      "type": "string",
      "description": "Scope: \"personal\" (default), \"team\" (auto-resolves), a team slug, or \"team:<id>\"."
    }
  }
}

connector_remove

Disconnect a connector. Pass slug.

Parameters3

slug	string	required	Connector slug to disconnect.
type	string	optional	Type of connector (mcp or oauth). Default: mcp.
billing	string	optional	Scope: "personal" (default), "team" (auto-resolves), a team slug, or "team:<id>".

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Connector slug to disconnect."
    },
    "type": {
      "type": "string",
      "enum": [
        "oauth",
        "mcp"
      ],
      "description": "Type of connector (mcp or oauth). Default: mcp."
    },
    "billing": {
      "type": "string",
      "description": "Scope: \"personal\" (default), \"team\" (auto-resolves), a team slug, or \"team:<id>\"."
    }
  },
  "required": [
    "slug"
  ]
}

brain_admin

Brain admin operations. Pass action: "lint" | "link" | "promote" | "rebuild_index" | "team_sleep". team_sleep enables/disables/runs the nightly team consolidation cycle — pass sub_action "enable" (with optional timezone), "disable", "status", or "run_now". Team admin role required for team_sleep actions.

Parameters8

action	string	required	Admin operation to perform.
page_id	string	optional	Source brain page ID (for link/promote).
to_page_id	string	optional	Target page ID (for link).
relationship	string	optional	Relationship type (for link, e.g. relates_to, derived_from).
label	string	optional	Human-readable relationship label (for link).
team_id	string	optional	Team to promote to (for promote). Auto-resolved if on one team.
sub_action	string	optional	Required for action="team_sleep". "enable" turns on nightly sleep for the team; "disable" turns it off; "status" shows last run and schedule; "run_now" triggers an immediate sleep cycle.
timezone	string	optional	IANA timezone for team_sleep enable (e.g. "Europe/London"). Defaults to UTC. Sleep fires at 3 AM local time.

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "lint",
        "link",
        "promote",
        "rebuild_index",
        "team_sleep"
      ],
      "description": "Admin operation to perform."
    },
    "page_id": {
      "type": "string",
      "description": "Source brain page ID (for link/promote)."
    },
    "to_page_id": {
      "type": "string",
      "description": "Target page ID (for link)."
    },
    "relationship": {
      "type": "string",
      "description": "Relationship type (for link, e.g. relates_to, derived_from)."
    },
    "label": {
      "type": "string",
      "description": "Human-readable relationship label (for link)."
    },
    "team_id": {
      "type": "string",
      "description": "Team to promote to (for promote). Auto-resolved if on one team."
    },
    "sub_action": {
      "type": "string",
      "enum": [
        "enable",
        "disable",
        "status",
        "run_now"
      ],
      "description": "Required for action=\"team_sleep\". \"enable\" turns on nightly sleep for the team; \"disable\" turns it off; \"status\" shows last run and schedule; \"run_now\" triggers an immediate sleep cycle."
    },
    "timezone": {
      "type": "string",
      "description": "IANA timezone for team_sleep enable (e.g. \"Europe/London\"). Defaults to UTC. Sleep fires at 3 AM local time."
    }
  },
  "required": [
    "action"
  ]
}

job_list

List your active and recent jobs. Optional status filter.

Parameters2

status	string	optional	Filter by job status.
limit	number	optional	Max jobs to return (default 20, max 100).

Raw schema

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "pending",
        "running",
        "completed",
        "failed",
        "cancelled"
      ],
      "description": "Filter by job status."
    },
    "limit": {
      "type": "number",
      "description": "Max jobs to return (default 20, max 100).",
      "minimum": 1,
      "maximum": 100
    }
  }
}

job_get

Get job status and result. Returns status: running | completed | failed and result when terminal. Keep polling until you get a terminal status.

Parameters1

job_id

string

required

The job ID returned when a long-running tool was called.

Raw schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job ID returned when a long-running tool was called."
    }
  },
  "required": [
    "job_id"
  ]
}

job_cancel

Cancel a running job.

Parameters1

job_id

string

required

The job ID to cancel.

Raw schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job ID to cancel."
    }
  },
  "required": [
    "job_id"
  ]
}

feedback_review

Submit a review or star rating.

Parameters3

tool	string	required	Tool name to review (e.g. "web-search" or "seo").
rating	number	required	Star rating 1-5 (1=poor, 3=okay, 5=excellent).
review	string	optional	Constructive feedback — what worked well and any specific suggestions to improve.

Raw schema

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "description": "Tool name to review (e.g. \"web-search\" or \"seo\")."
    },
    "rating": {
      "type": "number",
      "description": "Star rating 1-5 (1=poor, 3=okay, 5=excellent).",
      "minimum": 1,
      "maximum": 5
    },
    "review": {
      "type": "string",
      "description": "Constructive feedback — what worked well and any specific suggestions to improve."
    }
  },
  "required": [
    "tool",
    "rating"
  ]
}

feedback_debug

Report a ToolRouter platform bug that blocks you from completing the user's task. Use this when you suspect the issue is on our side — a tool crashed, returned malformed data, timed out unexpectedly, or behaved inconsistently. Include the relevant ToolRouter errors, call IDs, non-sensitive input shape, retries, and expected behavior. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets. Reports are stored and reviewed within hours. Skip this for expected errors like invalid input, missing credentials, insufficient balance, rate limits, or genuine "not found" results — those aren't bugs. Limit: 5 reports per hour.

Parameters10

tool	string	optional	Tool name that failed (e.g. "web-search").
skill	string	optional	Skill name that failed (e.g. "search").
error_messages	string	required	ALL error messages received during this interaction — not just the last one. Include the full text of every error response from ToolRouter, separated by newlines.
call_ids	string	optional	ALL call IDs from this interaction (successful and failed), one per line or comma-separated.
job_id	string	optional	Job ID for async jobs that failed, if applicable.
interaction_log	string	optional	Chronological log limited to the relevant ToolRouter calls: tool/skill names, non-sensitive input shape, response status, errors, retries, and job polling. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets.
input_summary	string	optional	Summary of what you sent to the failing tool (do NOT include API keys or secrets — describe the shape and intent).
expected_behavior	string	optional	What you expected to happen vs what actually happened.
agent_context	string	optional	MCP client name and version, if known.
severity	string	required	"blocking" = cannot complete task. "degraded" = partial results or workaround exists.

Raw schema

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "description": "Tool name that failed (e.g. \"web-search\")."
    },
    "skill": {
      "type": "string",
      "description": "Skill name that failed (e.g. \"search\")."
    },
    "error_messages": {
      "type": "string",
      "description": "ALL error messages received during this interaction — not just the last one. Include the full text of every error response from ToolRouter, separated by newlines."
    },
    "call_ids": {
      "type": "string",
      "description": "ALL call IDs from this interaction (successful and failed), one per line or comma-separated."
    },
    "job_id": {
      "type": "string",
      "description": "Job ID for async jobs that failed, if applicable."
    },
    "interaction_log": {
      "type": "string",
      "description": "Chronological log limited to the relevant ToolRouter calls: tool/skill names, non-sensitive input shape, response status, errors, retries, and job polling. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets."
    },
    "input_summary": {
      "type": "string",
      "description": "Summary of what you sent to the failing tool (do NOT include API keys or secrets — describe the shape and intent)."
    },
    "expected_behavior": {
      "type": "string",
      "description": "What you expected to happen vs what actually happened."
    },
    "agent_context": {
      "type": "string",
      "description": "MCP client name and version, if known."
    },
    "severity": {
      "type": "string",
      "enum": [
        "blocking",
        "degraded"
      ],
      "description": "\"blocking\" = cannot complete task. \"degraded\" = partial results or workaround exists."
    }
  },
  "required": [
    "error_messages",
    "severity"
  ]
}

feedback_request_tool

Ask ToolRouter to build a tool that does not exist yet. Use this when discover returned nothing useful for what the user needs. Describe the capability in plain terms — do not include personal data, API keys, or secrets. Requests go straight to the team. Limit: 5 per hour.

Parameters4

what	string	required	What the tool should do, in one or two sentences (e.g. "Look up UK company filings by company number").
why	string	optional	What the user was trying to accomplish and why existing tools did not fit.
searched	string	optional	The discover query you tried that came back empty.
agent_context	string	optional	MCP client name and version, if known.

Raw schema

{
  "type": "object",
  "properties": {
    "what": {
      "type": "string",
      "description": "What the tool should do, in one or two sentences (e.g. \"Look up UK company filings by company number\")."
    },
    "why": {
      "type": "string",
      "description": "What the user was trying to accomplish and why existing tools did not fit."
    },
    "searched": {
      "type": "string",
      "description": "The discover query you tried that came back empty."
    },
    "agent_context": {
      "type": "string",
      "description": "MCP client name and version, if known."
    }
  },
  "required": [
    "what"
  ]
}

top_up_credits

Add credits to your account. Returns a Stripe checkout URL — share it with the user to complete payment. Minimum $1.

Parameters1

amount_usd

number

required

Amount in USD to add (e.g. 10, 25, 50). Minimum $1.

Raw schema

{
  "type": "object",
  "properties": {
    "amount_usd": {
      "type": "number",
      "description": "Amount in USD to add (e.g. 10, 25, 50). Minimum $1.",
      "minimum": 1,
      "maximum": 500
    }
  },
  "required": [
    "amount_usd"
  ]
}

discover

Find the right ToolRouter tool for your task. Describe what you need in plain language. Examples: "analyze a website", "research competitors", "find prospect companies", "check DNS records". Exact tool name (e.g. "seo") returns full schemas and examples. Flow: prefer route({ intent }) to pick and run a tool. Use discover when you need schemas or a listing, then call use_tool(tool, skill, input). Every discover response also includes a top-level `connectors` array listing SaaS accounts the user has already connected (LinkedIn, Google, Notion, etc.). Use that to pick the right tool and account without asking — e.g. if `connectors` shows LinkedIn, the linkedin-post tool is ready to use. Categories: data, media, search, marketing, development, communication, analytics, productivity, ai, finance, security, infrastructure

Parameters2

query	string	required	What you want to do (e.g. "scrape a webpage"), a category (e.g. "security"), or "*" to list everything.
category	string	optional	Filter by category

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "What you want to do (e.g. \"scrape a webpage\"), a category (e.g. \"security\"), or \"*\" to list everything."
    },
    "category": {
      "type": "string",
      "description": "Filter by category",
      "enum": [
        "data",
        "media",
        "search",
        "marketing",
        "development",
        "communication",
        "analytics",
        "productivity",
        "ai",
        "finance",
        "security",
        "infrastructure"
      ]
    }
  },
  "required": [
    "query"
  ]
}

route

Send a natural-language intent and optionally any dimensions you already know (tool, skill, model, input fields). Fills only the blanks via Jev, then either executes the call or returns a ready-to-run use_tool payload. Explicit values are never overridden. Returns candidates when confidence is low or no tool fits. Flow: route → if confident and complete, result is returned; otherwise use the pre-filled call with use_tool.

Parameters6

intent	string	required	What you want to do, in plain language.
tool	string	optional	Optional. Tool name — honoured verbatim when set.
skill	string	optional	Optional. Skill name — honoured verbatim when set.
model	string	optional	Optional. Model override — honoured verbatim when set.
input	object	optional	Optional. Partial skill input — explicit fields are never overridden.
max_cost	number	optional	Optional. Max USD to spend; above this returns a pre-filled call instead of executing.

Raw schema

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "description": "What you want to do, in plain language."
    },
    "tool": {
      "type": "string",
      "description": "Optional. Tool name — honoured verbatim when set."
    },
    "skill": {
      "type": "string",
      "description": "Optional. Skill name — honoured verbatim when set."
    },
    "model": {
      "type": "string",
      "description": "Optional. Model override — honoured verbatim when set."
    },
    "input": {
      "type": "object",
      "description": "Optional. Partial skill input — explicit fields are never overridden."
    },
    "max_cost": {
      "type": "number",
      "description": "Optional. Max USD to spend; above this returns a pre-filled call instead of executing."
    }
  },
  "required": [
    "intent"
  ]
}

use_tool

Call a ToolRouter catalogue tool. Prefer `route` with a natural-language intent when you do not already know the tool and skill — it picks them, fills arguments, and runs the call. Use discover when you need schemas or a catalogue listing, then pass the exact tool name and skill here. IMPORTANT: "discover", "route", "credits_balance", and other built-in tools are NOT catalogue tools — call them directly, never through use_tool. Long-running tools return a job_id — poll with job_get. If a skill needs an image_url or file URL and you have a local file or base64 image, use file_write first to get a hosted URL, then pass that URL to the skill. BRAIN: Some tools require you to consult brain_query first. If use_tool returns an error about brain_context, call brain_query with a relevant query, then pass the result text as brain_context in your use_tool input.

Parameters7

tool	string	required	Tool reference from discover results, e.g. "web-search"
skill	string	required	Skill name from discover results, e.g. "search"
input	object	required	Skill input parameters (see discover for schema). For persona-using tools, include persona_file_id from discover or persona_list. For scene-using tools, include scene_file_id from discover or scene_list. For product-using tools, include product_file_id from discover or product_list. For outfit-using tools, include outfit_file_id from discover or outfit_list. For style-reference tools, include style_reference_id (from discover or file_list), style_reference_query (semantic search), or style_reference_prompt (inline prose). For image-composition tools (e.g. generate-image image_to_image), pass any combination of scene_file_id, persona_file_id, product_file_ids[] (from file_list section "products"), outfit_file_ids[] (section "outfits"), and raw image_urls[] — the gateway resolves and merges them into a single image_urls array (max 4 by default).
response_format	string	optional	Response verbosity. "concise" (default) strips noise, returns essential data only. "detailed" returns everything including raw metadata.
backend	object	optional	Route the same model through interchangeable providers. order prioritises providers; only restricts; ignore excludes; allow_fallbacks defaults true.
billing	string	optional	Which account to bill. "personal", "team" (auto-resolves if on one team), a team slug ("humanleap"), or a team ID ("team:m57df8c..."). Omit to use your default.
brain_context	string	optional	Brain knowledge from brain_query. Pass at the top level of use_tool (alongside "tool", "skill", "input") — NOT inside input. Call brain_query first, then paste the result text here to clear the brain gate.

Raw schema

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "description": "Tool reference from discover results, e.g. \"web-search\""
    },
    "skill": {
      "type": "string",
      "description": "Skill name from discover results, e.g. \"search\""
    },
    "input": {
      "type": "object",
      "description": "Skill input parameters (see discover for schema). For persona-using tools, include persona_file_id from discover or persona_list. For scene-using tools, include scene_file_id from discover or scene_list. For product-using tools, include product_file_id from discover or product_list. For outfit-using tools, include outfit_file_id from discover or outfit_list. For style-reference tools, include style_reference_id (from discover or file_list), style_reference_query (semantic search), or style_reference_prompt (inline prose). For image-composition tools (e.g. generate-image image_to_image), pass any combination of scene_file_id, persona_file_id, product_file_ids[] (from file_list section \"products\"), outfit_file_ids[] (section \"outfits\"), and raw image_urls[] — the gateway resolves and merges them into a single image_urls array (max 4 by default)."
    },
    "response_format": {
      "type": "string",
      "description": "Response verbosity. \"concise\" (default) strips noise, returns essential data only. \"detailed\" returns everything including raw metadata.",
      "enum": [
        "concise",
        "detailed"
      ],
      "default": "concise"
    },
    "backend": {
      "type": "object",
      "description": "Route the same model through interchangeable providers. order prioritises providers; only restricts; ignore excludes; allow_fallbacks defaults true.",
      "properties": {
        "order": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Provider slugs to try first, in order."
        },
        "only": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Restrict the call to these providers."
        },
        "ignore": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Exclude these providers."
        },
        "allow_fallbacks": {
          "type": "boolean",
          "description": "Try the next provider after an outage, timeout, or rate limit. Defaults to true."
        }
      },
      "additionalProperties": false
    },
    "billing": {
      "type": "string",
      "description": "Which account to bill. \"personal\", \"team\" (auto-resolves if on one team), a team slug (\"humanleap\"), or a team ID (\"team:m57df8c...\"). Omit to use your default."
    },
    "brain_context": {
      "type": "string",
      "description": "Brain knowledge from brain_query. Pass at the top level of use_tool (alongside \"tool\", \"skill\", \"input\") — NOT inside input. Call brain_query first, then paste the result text here to clear the brain gate."
    }
  },
  "required": [
    "tool",
    "skill",
    "input"
  ]
}

brain_query

Search your knowledge brain for relevant information. Returns pages ranked by relevance. Optional wing/hall narrow the search to a slice of the brain (e.g. wing="engineering", hall="preference").

Parameters7

query	string	optional	Search query. Omit to list all pages by recency.
scope	string	optional	Which brain scope to search. Defaults to all.
limit	number	optional	Max results. Defaults to 10.
wing	string	optional	Optional. Restrict to a specific wing (top-level area like "engineering", "family").
hall	string	optional	Optional. Restrict to a hall: "fact", "event", "discovery", "preference", or "advice".
include_drawer_previews	boolean	optional	Optional. When true, each result includes the first ~400 chars of its linked drawer (raw source text) if one exists. Useful to decide whether to call brain_expand for the full text.
as_of	string	optional	Optional. ISO-date string (e.g. "2026-01-15"). When set, returns pages that were valid at that point in time — including superseded versions. Useful for "what did we know in January?" queries.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query. Omit to list all pages by recency."
    },
    "scope": {
      "type": "string",
      "enum": [
        "personal",
        "team",
        "all"
      ],
      "description": "Which brain scope to search. Defaults to all."
    },
    "limit": {
      "type": "number",
      "description": "Max results. Defaults to 10."
    },
    "wing": {
      "type": "string",
      "description": "Optional. Restrict to a specific wing (top-level area like \"engineering\", \"family\")."
    },
    "hall": {
      "type": "string",
      "description": "Optional. Restrict to a hall: \"fact\", \"event\", \"discovery\", \"preference\", or \"advice\"."
    },
    "include_drawer_previews": {
      "type": "boolean",
      "description": "Optional. When true, each result includes the first ~400 chars of its linked drawer (raw source text) if one exists. Useful to decide whether to call brain_expand for the full text."
    },
    "as_of": {
      "type": "string",
      "description": "Optional. ISO-date string (e.g. \"2026-01-15\"). When set, returns pages that were valid at that point in time — including superseded versions. Useful for \"what did we know in January?\" queries."
    }
  },
  "required": []
}

brain_add

Create a new brain page. Knowledge you add here will be available to all future tool calls. Optional wing/room/hall organise the page in the MemPalace hierarchy for sharper retrieval.

Parameters8

title	string	required	Page title
content	string	required	Page content (markdown)
scope	string	optional	Visibility scope. Defaults to personal.
tags	array	optional	Tags for categorisation
wing	string	optional	Optional. Top-level area (e.g. "engineering", "family", "general"). Auto-classified if omitted.
room	string	optional	Optional. Sub-area within the wing (e.g. "databases", "deploy"). Defaults to "untagged".
hall	string	optional	Optional. One of "fact", "event", "discovery", "preference", "advice". Defaults to "fact".
load_tier	string	optional	Optional. L0 = operator identity (rare), L1 = always-loaded critical fact, L2 = default on-demand, L3 = cold archive. Omit to default to L2.

Raw schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Page title"
    },
    "content": {
      "type": "string",
      "description": "Page content (markdown)"
    },
    "scope": {
      "type": "string",
      "enum": [
        "personal",
        "team"
      ],
      "description": "Visibility scope. Defaults to personal."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tags for categorisation"
    },
    "wing": {
      "type": "string",
      "description": "Optional. Top-level area (e.g. \"engineering\", \"family\", \"general\"). Auto-classified if omitted."
    },
    "room": {
      "type": "string",
      "description": "Optional. Sub-area within the wing (e.g. \"databases\", \"deploy\"). Defaults to \"untagged\"."
    },
    "hall": {
      "type": "string",
      "description": "Optional. One of \"fact\", \"event\", \"discovery\", \"preference\", \"advice\". Defaults to \"fact\"."
    },
    "load_tier": {
      "type": "string",
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3"
      ],
      "description": "Optional. L0 = operator identity (rare), L1 = always-loaded critical fact, L2 = default on-demand, L3 = cold archive. Omit to default to L2."
    }
  },
  "required": [
    "title",
    "content"
  ]
}

brain_update

Edit an existing brain page's content or metadata. wing/room/hall can be patched to re-file a page. scope can be changed to move a page between your personal and team brain — useful when an auto-ingested page landed in the wrong place. Moving a page to team scope requires team admin role.

Parameters10

page_id	string	required	Brain page ID (bp_...)
content	string	optional	New content (replaces existing)
title	string	optional	New title
tags	array	optional	New tags
wing	string	optional	Optional. Re-file under a different wing.
room	string	optional	Optional. Re-file under a different room.
hall	string	optional	Optional. Change hall: fact / event / discovery / preference / advice.
load_tier	string	optional	Optional. Change load tier. L1 promotes a page to always-loaded; L3 sends it to cold archive.
scope	string	optional	Optional. Move the page between your personal and team brain. Moving TO team requires team admin role and a team billing context. Moving FROM team to personal is allowed if you own the page or are an admin.
material_change	boolean	optional	Optional. When true, creates a new version of the page — the old version is preserved with a timestamp and a "supersedes" link. Use for corrections or significant changes; skip for minor edits. Default false.

Raw schema

{
  "type": "object",
  "properties": {
    "page_id": {
      "type": "string",
      "description": "Brain page ID (bp_...)"
    },
    "content": {
      "type": "string",
      "description": "New content (replaces existing)"
    },
    "title": {
      "type": "string",
      "description": "New title"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "New tags"
    },
    "wing": {
      "type": "string",
      "description": "Optional. Re-file under a different wing."
    },
    "room": {
      "type": "string",
      "description": "Optional. Re-file under a different room."
    },
    "hall": {
      "type": "string",
      "description": "Optional. Change hall: fact / event / discovery / preference / advice."
    },
    "load_tier": {
      "type": "string",
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3"
      ],
      "description": "Optional. Change load tier. L1 promotes a page to always-loaded; L3 sends it to cold archive."
    },
    "scope": {
      "type": "string",
      "enum": [
        "personal",
        "team"
      ],
      "description": "Optional. Move the page between your personal and team brain. Moving TO team requires team admin role and a team billing context. Moving FROM team to personal is allowed if you own the page or are an admin."
    },
    "material_change": {
      "type": "boolean",
      "description": "Optional. When true, creates a new version of the page — the old version is preserved with a timestamp and a \"supersedes\" link. Use for corrections or significant changes; skip for minor edits. Default false."
    }
  },
  "required": [
    "page_id"
  ]
}

brain_delete

Archive a brain page. It will no longer appear in searches or tool consultations.

Parameters1

page_id

string

required

Brain page ID (bp_...) to archive

Raw schema

{
  "type": "object",
  "properties": {
    "page_id": {
      "type": "string",
      "description": "Brain page ID (bp_...) to archive"
    }
  },
  "required": [
    "page_id"
  ]
}

brain_status

View brain page counts and recent pages for your personal and team brain.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "required": []
}

brain_lint

Run maintenance checks on your brain: find stale pages, orphaned knowledge, and other issues.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "required": []
}

brain_settings

View and toggle your brain settings. Currently supports: drawers_enabled (store raw tool output alongside summaries for richer recall).

Parameters3

action	string	required	"get" lists current settings; "set" toggles a named setting.
setting	string	optional	Setting name (required for "set"). Currently: "drawers_enabled".
value	boolean	optional	New value (required for "set").

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "set"
      ],
      "description": "\"get\" lists current settings; \"set\" toggles a named setting."
    },
    "setting": {
      "type": "string",
      "description": "Setting name (required for \"set\"). Currently: \"drawers_enabled\"."
    },
    "value": {
      "type": "boolean",
      "description": "New value (required for \"set\")."
    }
  },
  "required": [
    "action"
  ]
}

brain_expand

Retrieve the verbatim source text (a "drawer") linked from a brain page. Use this when a summary lacks specifics you need — drawers contain the original tool output, redacted for credentials. Returns 404 if the page has no linked drawer (not all pages do — drawers are a Step 4 feature for allowlisted tools only).

Parameters1

page_id

string

required

Brain page ID (bp_...) whose drawer to expand.

Raw schema

{
  "type": "object",
  "properties": {
    "page_id": {
      "type": "string",
      "description": "Brain page ID (bp_...) whose drawer to expand."
    }
  },
  "required": [
    "page_id"
  ]
}

brain_wings

List the wings of your brain — the top-level areas your knowledge is organised under (e.g. "engineering", "family"). For each wing returns the rooms and halls inside, page count, and last-updated time. Use this to discover the right wing/hall to pass to brain_query.

Parameters1

include_team

boolean

optional

If true, also count team-scope pages. Default false (personal only).

Raw schema

{
  "type": "object",
  "properties": {
    "include_team": {
      "type": "boolean",
      "description": "If true, also count team-scope pages. Default false (personal only)."
    }
  },
  "required": []
}

connector_permissions

View or set permissions for tools on a connected MCP server — which tools are allowed, rate limits, budget caps, argument restrictions. Pass the connector slug (from connector_list) and action: "list" to see current rules, or action: "set" with tool_name + rules to update one. Team scope requires admin role.

Parameters15

slug	string	required	Connector slug.
action	string	optional	Omit to list permissions for all tools. Pass "set" with tool_name + rules to update one.
billing	string	optional	Scope: "personal", "team" (auto-resolves if on one team), a team slug, or "team:<id>".
tool_name	string	optional	Tool name (for set). Use "*" for all tools on this connector.
allowed	boolean	optional	Whether the tool is allowed (for set).
rate_limit_per_hour	number	optional	Max calls per hour, per user (for set).
rate_limit_per_day	number	optional	Max calls per day, per user (for set).
team_rate_limit_per_hour	number	optional	Max calls per hour, team-wide (for set).
team_rate_limit_per_day	number	optional	Max calls per day, team-wide (for set).
cost_per_call	number	optional	Cost in millicents per call (for set).
budget_per_day	number	optional	Max daily spend per user, in millicents (for set).
team_budget_per_day	number	optional	Max daily spend team-wide, in millicents (for set).
arg_schema_rules	string	optional	JSON Schema validating tool arguments (for set). Example: {"properties":{"channel":{"enum":["#general"]}}}
arg_natural_language_rules	string	optional	Plain English rules for argument filtering (for set). Example: "Only allow queries for the last 90 days."
nl_filter_mode	string	optional	How to enforce NL rules: strict (block on violation) or advisory (log only). Default: strict.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Connector slug."
    },
    "action": {
      "type": "string",
      "enum": [
        "list",
        "set"
      ],
      "description": "Omit to list permissions for all tools. Pass \"set\" with tool_name + rules to update one."
    },
    "billing": {
      "type": "string",
      "description": "Scope: \"personal\", \"team\" (auto-resolves if on one team), a team slug, or \"team:<id>\"."
    },
    "tool_name": {
      "type": "string",
      "description": "Tool name (for set). Use \"*\" for all tools on this connector."
    },
    "allowed": {
      "type": "boolean",
      "description": "Whether the tool is allowed (for set)."
    },
    "rate_limit_per_hour": {
      "type": "number",
      "description": "Max calls per hour, per user (for set)."
    },
    "rate_limit_per_day": {
      "type": "number",
      "description": "Max calls per day, per user (for set)."
    },
    "team_rate_limit_per_hour": {
      "type": "number",
      "description": "Max calls per hour, team-wide (for set)."
    },
    "team_rate_limit_per_day": {
      "type": "number",
      "description": "Max calls per day, team-wide (for set)."
    },
    "cost_per_call": {
      "type": "number",
      "description": "Cost in millicents per call (for set)."
    },
    "budget_per_day": {
      "type": "number",
      "description": "Max daily spend per user, in millicents (for set)."
    },
    "team_budget_per_day": {
      "type": "number",
      "description": "Max daily spend team-wide, in millicents (for set)."
    },
    "arg_schema_rules": {
      "type": "string",
      "description": "JSON Schema validating tool arguments (for set). Example: {\"properties\":{\"channel\":{\"enum\":[\"#general\"]}}}"
    },
    "arg_natural_language_rules": {
      "type": "string",
      "description": "Plain English rules for argument filtering (for set). Example: \"Only allow queries for the last 90 days.\""
    },
    "nl_filter_mode": {
      "type": "string",
      "enum": [
        "strict",
        "advisory"
      ],
      "description": "How to enforce NL rules: strict (block on violation) or advisory (log only). Default: strict."
    }
  },
  "required": [
    "slug"
  ]
}

README.md8 KBView on GitHub

ToolRouter — the OpenRouter for tools

The OpenRouter for tools. One MCP connection gives any AI agent 250+ hosted tools, pay per call.

ToolRouter is the OpenRouter for tools. Connect once over MCP and your agent can discover and call 250+ hosted specialist tools: web search, scraping, image and video generation, SEO, finance, property, compliance and more. Free tools work immediately; paid tools are pay per call. Everything runs on the hosted gateway; nothing executes locally.

The compact routing surface costs an agent about 9,000 tokens of context for the whole catalog, versus roughly 257,000 tokens if every skill were loaded as its own tool (measured 2026-09-03; method and raw data at https://toolrouter.com/blog/mcp-tool-schema-token-cost).

Connect in one line

Hosted endpoint: https://api.toolrouter.com/mcp (streamable HTTP). No API key needed — the server provisions a free account on first connect and returns a claim link.

Claude Code

bash

claude mcp add --transport http toolrouter https://api.toolrouter.com/mcp

Claude (chat, Desktop, mobile)

Customize → Connectors → Add custom connector, name it ToolRouter, URL https://api.toolrouter.com/mcp/anthropic.

Cursor

Add to .cursor/mcp.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "url": "https://api.toolrouter.com/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json:

json

{
  "servers": {
    "toolrouter": {
      "type": "http",
      "url": "https://api.toolrouter.com/mcp"
    }
  }
}

Gemini CLI

Add to ~/.gemini/settings.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "httpUrl": "https://api.toolrouter.com/mcp"
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "serverUrl": "https://api.toolrouter.com/mcp"
    }
  }
}

Any other MCP client that speaks streamable HTTP can use the same URL.

Local bridge (npm)

toolrouter-mcp is a stdio bridge to the same hosted gateway, plus a CLI. Use it where a client cannot take a remote URL.

Three ways to use it

1. MCP Server (for AI agents)

Run with no arguments to start an MCP stdio server. No API key needed — auto-provisions on first use:

bash

npx -y toolrouter-mcp

2. CLI (for terminal workflows)

bash

npx -y toolrouter-mcp tools                    # list all tools
npx -y toolrouter-mcp search "web scraping"    # search by keyword
npx -y toolrouter-mcp call seo analyze_page --url https://example.com
npx -y toolrouter-mcp help

3. REST API (direct HTTP)

bash

# Get an API key (or use one from ~/.toolrouter/key after MCP setup)
curl -X POST https://api.toolrouter.com/v1/auth/provision

curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
  -d '{"tool":"seo","skill":"analyze_page","input":{"url":"https://example.com"}}' \
  https://api.toolrouter.com/v1/tools/call

Install the local bridge

Codex CLI

bash

codex mcp add toolrouter -- npx -y toolrouter-mcp

Cursor

Add to .cursor/mcp.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

OpenClaw

Add to openclaw.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

Cline

Open MCP settings and add:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

VS Code

Add to .vscode/mcp.json:

json

{
  "servers": {
    "toolrouter": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

Gemini CLI

Add to your Gemini CLI settings:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": ["-y", "toolrouter-mcp"]
    }
  }
}

API Key

No setup needed — toolrouter-mcp auto-provisions a free API key on first use and caches it to ~/.toolrouter/key. Free tools work immediately. For paid tools, visit the claim URL printed on first run to add credits.

To use an existing key instead: set TOOLROUTER_API_KEY=tr_live_xxx as an environment variable.

How It Works

This package serves two purposes from one binary:

MCP mode (no args): Starts an MCP stdio server that proxies tools/list and tools/call to the ToolRouter API via Streamable HTTP.
CLI mode (tools/search/call/help): Thin HTTP client that sends requests to the ToolRouter API and prints results. No local tool execution.

Both modes go through https://api.toolrouter.com — all processing happens on ToolRouter's infrastructure.

MCP Meta-Tools

When connected via MCP, your agent gets meta-tools for tool discovery, execution, async jobs, and full account management:

Discovery & execution:

Tool	Description
`discover`	Find tools by keyword, category, or `*` for all
`use_tool`	Execute a tool skill
`job_get`	Poll an async job's status and result
`job_list`	List recent async jobs
`job_cancel`	Cancel a running async job

Credits & billing:

Tool	Description
`credits_balance`	Get available credit balance
`credits_usage`	Usage breakdown and recent call history
`top_up_credits`	Add credits
`subscription_manage`	View or change your subscription
`invoice_list`	List invoices

API keys:

Tool	Description
`key_create`	Create a new API key
`key_list`	List API keys
`key_delete`	Permanently disable an API key

Credentials (BYOK):

Tool	Description
`credential_save`	Save your own provider API key
`credential_list`	List saved credentials
`credential_delete`	Remove a saved credential
`credential_default`	Set the default credential for a provider

Connectors & account:

Tool	Description
`connector_add`	Connect a SaaS account via OAuth
`connector_list`	List connected accounts
`account_preferences`	View and update account settings
`feedback_review`	Rate a tool

Environment Variables

Variable	Required	Default	Description
`TOOLROUTER_API_KEY`	Yes (for tool calls)	—	Your API key
`TOOLROUTER_API_URL`	No	`https://api.toolrouter.com`	Custom API endpoint

CLI Reference

Command	Auth Required	Description
`tools`	No	List all available tools
`search <query>`	No	Search tools by keyword
`call <tool> <skill> [opts]`	Yes	Call a tool skill
`help`	No	Show usage help

Input methods for `call`

bash

# Flag-based (most common)
npx -y toolrouter-mcp call humanleap/seo analyze_page --url https://example.com

# JSON string
npx -y toolrouter-mcp call humanleap/web-search search --input '{"query":"MCP tools"}'

Requirements

Node.js 22+

Privacy Policy

https://toolrouter.com/privacy

Support

support@toolrouter.com

Install

Tools (48)

account_setupaccount_listaccount_switchaccount_preferencescredits_balancecredits_usagesubscription_manageinvoice_list

Remote endpoint

Streamable HTTP

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

url

https://api.toolrouter.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "toolrouter": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.toolrouter.com/mcp"
      ]
    }
  }
}

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