clichefactory-mcp

MCP (Model Context Protocol) server for ClicheFactory — structured data extraction from documents.

This server exposes ClicheFactory's extraction and document conversion capabilities as MCP tools, allowing AI assistants in Cursor, Claude Desktop, OpenClaw, and other MCP-compatible clients to extract structured data from PDFs, images, DOCX, XLSX, CSV, EML, and more.

Tools

extract

The main tool. Pass a document file and a JSON schema — get structured data back.

Supports all extraction modes:

The schema can be provided as:

• File path: absolute path to a .json schema file
• Inline dict: the LLM constructs a JSON schema from the conversation (e.g., the user says "extract the invoice number and total" and the LLM builds {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}})

to_markdown

Converts any supported document to markdown. Useful for inspecting document contents or feeding them to the LLM for analysis before deciding on an extraction schema.

doctor

Runs diagnostics on the ClicheFactory setup — config file, API keys, Python dependencies, system binaries. Call this when things aren't working.

Execution Modes

The server supports two modes, matching the SDK and CLI:

• local — Runs extraction on your machine. You bring your own LLM key (BYOK). Supports Gemini, OpenAI, Anthropic, and Ollama models. Requires the clichefactory[local] dependencies for document parsing.

• service — Uses the ClicheFactory cloud service. Requires a ClicheFactory API key. Supports all extraction modes including trained pipelines and robust verification. Optionally accepts BYOK model overrides.

Installation

Prerequisites

• Python ≥ 3.12
• uv (recommended) or pip

From PyPI

pip install clichefactory-mcp

For local-mode extraction (document parsing on your machine), install with the local extras:

pip install "clichefactory-mcp[local]"

Configuration

Environment Variables

Set these in your MCP client configuration (see below) or in ~/.clichefactory/config.toml via clichefactory configure.

The config file at ~/.clichefactory/config.toml (created by clichefactory configure) is also respected. Environment variables take precedence over the config file.

Cursor

Add to .cursor/mcp.json in your project (or global Cursor settings):

{
  "mcpServers": {
    "clichefactory": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/cliche-mcp", "run", "clichefactory-mcp"],
   

... [View full README on GitHub](https://github.com/clichefactory/clichefactory-mcp#readme)