Clichefactory Mcp

Name: Clichefactory Mcp
Author: ClicheFactory

by ClicheFactorycommunityv0.1.8

MCP server for ClicheFactory that extracts structured JSON from documents and converts supported files to markdown. It supports local or cloud service execution for PDFs, images, office documents, CSVs, EML, and text files.

From the registry: Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.

GitHub Repository Website

Install & configure

Prerequisites

required
Install Python 3.12+
Python 3.12 or newer is required to run the MCP server.
required
Install uv or pip
Install uv (recommended) or pip to install/run the package. The simplest portable config path uses uvx.
https://docs.astral.sh/uv/
required
Install the MCP package
Install the server from PyPI. Use the local extras if you want local-mode document parsing on your machine.
```
$ pip install clichefactory-mcp
# or for local mode:
pip install "clichefactory-mcp[local]"
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `clichefactory-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Python 3.12+** — Python 3.12 or newer is required to run the MCP server.
- **Install uv or pip** — Install uv (recommended) or pip to install/run the package. The simplest portable config path uses uvx. (https://docs.astral.sh/uv/)
- **Install the MCP package** — Install the server from PyPI. Use the local extras if you want local-mode document parsing on your machine. Run: `pip install clichefactory-mcp
# or for local mode:
pip install "clichefactory-mcp[local]"`

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["clichefactory-mcp"]
- optional environment variables:
  - `CLICHEFACTORY_API_KEY`: ClicheFactory API key for service mode. (example: `<your-clichefactory-api-key>`)
  - `CLICHEFACTORY_API_URL`: Override the default ClicheFactory service URL, useful for self-hosted or development backends. (example: `<your-clichefactory-api-url>`)
  - `LLM_MODEL_NAME`: Model name for local mode, for example a Gemini, OpenAI, Anthropic, or Ollama model identifier. (example: `<your-llm-model-name>`)
  - `LLM_API_KEY`: API key for the LLM provider used in local mode. (example: `<your-llm-api-key>`)
  - `OCR_MODEL_NAME`: Optional separate OCR/VLM model name; defaults to the main model. (example: `<your-ocr-model-name>`)
  - `OCR_API_KEY`: Optional API key for the OCR model; defaults to the main LLM key. (example: `<your-ocr-api-key>`)

Note: Choose one execution mode: service mode typically requires CLICHEFACTORY_API_KEY; local mode typically requires both LLM_MODEL_NAME and LLM_API_KEY. If using local mode, install the package with the [local] extra.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Choose one execution mode: service mode typically requires CLICHEFACTORY_API_KEY; local mode typically requires both LLM_MODEL_NAME and LLM_API_KEY. If using local mode, install the package with the [local] extra.