Advertise
MCP.so
Sign In

Mistral OCR MCP Server

@sathizz7

Repository

Basic information

Category

Other

Transports

stdio

Author

sathizz7

About Mistral OCR MCP Server

Mcp ocr server

#mistral-ocr#ocr-server#mcp

Mistral OCR MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "MCP-Mistral-Ocr": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Mistral OCR MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Mistral OCR MCP Server?

Mistral OCR MCP Server is a local OCR server built with FastAPI that uses Mistral OCR to perform text extraction from uploaded images. It is compliant with the Model Context Protocol (MCP), enabling interaction via an MCP interface. The server is designed for developers who need a self-hosted, standards‑based OCR service that can be integrated into MCP‑aware applications.

How to use Mistral OCR MCP Server?

Install dependencies with pip install . (Python 3.10+ required). Start the server using uvicorn main:app --reload, which runs on http://127.0.0.1:8000. Submit an image for OCR via POST /v1/ocr with a multipart/form-data file field, or interact through the MCP endpoint at BASE_URL/mcp. A GET /health endpoint checks server status.

Key features of Mistral OCR MCP Server

  • FastAPI backend for high‑performance HTTP and MCP endpoints.
  • RESTful OCR endpoint (POST /v1/ocr) with file upload support.
  • MCP‑compliant interface for tool‑based interaction.
  • Configuration via Pydantic settings and environment variables.
  • Integrated logging and health check endpoint.
  • Default support for common image formats (JPEG, PNG) and a 1 MB upload limit.

Use cases of Mistral OCR MCP Server

  • Extract text from images in a local, self‑hosted environment.
  • Integrate OCR capabilities into MCP‑compatible applications and agents.
  • Prototype and test OCR pipelines with a simple REST API.
  • Process sensitive documents without sending data to external cloud services.
  • Build custom document‑processing workflows with configurable file type limits.

Frequently asked questions

1

What are the runtime requirements?

Python 3.10 or higher is required. The server runs locally using `pip` or `uv` for package management. No external cloud credentials are needed.

2

Which file types and size are supported?

By default, the server accepts `image/jpeg` and `image/png` files. The maximum upload size is set to 1 MB (configurable via environment variables).

3

How do I configure the server?

Configuration options (e.g., supported file types, model settings) are defined in `ocr/config.py` using Pydantic. They can be overridden with environment variables. Refer to the config file for available settings.

4

Does the server support authentication?

No authentication is mentioned in the documentation. The server is intended for local or internal network use.

5

What transport protocols are available?

The server provides both REST (HTTP) and MCP transports. The REST endpoint is at `/v1/ocr`, and the MCP endpoint is at `BASE_URL/mcp`.

Comments

More Other MCP servers

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K
Advertise