classifier.dev docs
classifier.dev documentation as tools: list, read and search the reference, benchmark and guides.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"docs": {
"url": "https://classifier.dev/mcp/docs"
}
}
}Remote endpoints
https://classifier.dev/mcp/docsstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢list_docs(filter)
List every classifier.dev document available over this server — the API reference, the benchmark, the agent skill, the CLI, pricing, privacy, terms and the MCP setup guide — with an id, a title, its section headings and its size. Call this first, then read_doc for the one you need.
Input Schema
{
"type": "object",
"properties": {
"filter": {
"type": "string",
"maxLength": 100,
"description": "Optional: only documents whose id, title or section headings contain this text (case-insensitive)."
}
},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"docs": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"sections": {
"type": "array",
"items": {
"type": "string"
}
},
"chars": {
"type": "integer"
}
},
"required": [
"id",
"title",
"url"
]
}
}
},
"required": [
"docs"
]
}🟢read_doc(id, section)
Return one document in full, or just one of its sections. ids: api, developers, mcp-setup, benchmark, skill, llms, pricing, auth, agents, privacy, terms, about, contact. Use section to fetch a single heading (case-insensitive prefix match) when the whole document is more than you need.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"enum": [
"api",
"developers",
"mcp-setup",
"benchmark",
"skill",
"llms",
"pricing",
"auth",
"agents",
"privacy",
"terms",
"about",
"contact"
],
"description": "Which document."
},
"section": {
"type": "string",
"description": "Optional heading to return on its own, e.g. \"limits\" or \"parameters\"."
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢search_docs(query, limit)
Full-text search across every classifier.dev document. Returns the paragraphs that contain all of your query's words, with the document and section each came from. Use it for a specific question — rate limits, how confidence is calibrated, how to connect from Claude or ChatGPT — instead of reading whole documents.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"maxLength": 200,
"description": "Words to look for; all must appear in a paragraph."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_examples(client, multi_label)
Return a copy-pasteable example of calling classifier.dev from a given client: curl, javascript (fetch), python (requests), the classify CLI, or an MCP tools/call payload. Use this when you are about to write integration code and want the exact request shape rather than reading the whole reference.
Input Schema
{
"type": "object",
"properties": {
"client": {
"type": "string",
"enum": [
"curl",
"javascript",
"python",
"cli",
"mcp"
],
"description": "Which client to show."
},
"multi_label": {
"type": "boolean",
"default": false,
"description": "Show the multi-label form (every label that applies) instead of single-label."
}
},
"required": [
"client"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"client": {
"type": "string"
},
"code": {
"type": "string"
},
"notes": {
"type": "string"
}
},
"required": [
"client",
"code"
]
}Community
Evidence