Mistral OCR
About
Processes images and PDFs through Mistral AI's OCR API to extract text from visual documents, supporting both local files and URLs with Docker containerization for easy deployment.
Details
- Author
- everaldo
- Repository
- everaldo/mcp-mistral-ocr
- GitHub stars
- 32
- Downloads
- 313
- License
- MIT License
- Categories
- Productivity, Other, AI, Developer Tools, Design, Workplace, File Management, Media, Frontend, Security, Infrastructure
- Tags
- #web
Jump to
- Process local files (images and PDFs) using Mistral's OCR
- Process files from URLs with explicit file type specification
- Support for multiple file formats (JPG, PNG, PDF, etc.)
- Results saved as JSON files with timestamps
- Docker containerization
- UV package management
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mistral OCRCommand (node, npx, python, etc.)dockerArguments-
Argument 1
run -
Argument 2
-i -
Argument 3
--rm -
Argument 4
-e -
Argument 5
MISTRAL_API_KEY -
Argument 6
-e -
Argument 7
OCR_DIR -
Argument 8
-v -
Argument 9
C:/path/to/your/files:/data/ocr -
Argument 10
mcp-mistral-ocr:latest
Environment-
OCR_DIR
C:/path/to/your/files -
MISTRAL_API_KEY
<YOUR_MISTRAL_API_KEY>
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- MISTRAL_API_KEY: Your Mistral AI API key
- OCR_DIR: Directory path for local file processing. Inside the container, this is always mapped to /data/ocr
To install Mistral OCR for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @everaldo/mcp/mistral-crosswalk --client claude
Add this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"mistral-ocr": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MISTRAL_API_KEY",
"-e",
"OCR_DIR",
"-v",
"C:/path/to/your/files:/data/ocr",
"mcp-mistral-ocr:latest"
],
"env": {
"MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>",
"OCR_DIR": "C:/path/to/your/files"
}
}
}
}
process_local_file
Process a file from the configured OCR_DIR directory. Parameters: filename (string) - the name of the file to process.
process_url_file
Process a file from a URL. Requires explicit file type specification. Parameters: url (string) - the URL of the file to process, file_type (string) - the type of file ('image' or 'pdf').
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mistral ocr": {
"env": {
"OCR_DIR": "C:/path/to/your/files",
"MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>"
},
"args": [
"run",
"-i",
"--rm",
"-e",
"MISTRAL_API_KEY",
"-e",
"OCR_DIR",
"-v",
"C:/path/to/your/files:/data/ocr",
"mcp-mistral-ocr:latest"
],
"command": "docker"
}
}
}Linux
{
"env": {
"OCR_DIR": "C:/path/to/your/files",
"MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>"
},
"args": [
"run",
"-i",
"--rm",
"-e",
"MISTRAL_API_KEY",
"-e",
"OCR_DIR",
"-v",
"C:/path/to/your/files:/data/ocr",
"mcp-mistral-ocr:latest"
],
"command": "docker"
}Macos
{
"env": {
"OCR_DIR": "C:/path/to/your/files",
"MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>"
},
"args": [
"run",
"-i",
"--rm",
"-e",
"MISTRAL_API_KEY",
"-e",
"OCR_DIR",
"-v",
"C:/path/to/your/files:/data/ocr",
"mcp-mistral-ocr:latest"
],
"command": "docker"
}Windows
{
"env": {
"OCR_DIR": "C:/path/to/your/files",
"MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>"
},
"args": [
"run",
"-i",
"--rm",
"-e",
"MISTRAL_API_KEY",
"-e",
"OCR_DIR",
"-v",
"C:/path/to/your/files:/data/ocr",
"mcp-mistral-ocr:latest"
],
"command": "docker"
}MCP Mistral OCR
An MCP server that provides OCR capabilities using Mistral AI's OCR API. This server can process both local files and URLs, supporting images and PDFs.
<a href="https://glama.ai/mcp/servers/@everaldo/mcp-mistral-ocr">
</a>
Features
- Process local files (images and PDFs) using Mistral's OCR
- Process files from URLs with explicit file type specification
- Support for multiple file formats (JPG, PNG, PDF, etc.)
- Results saved as JSON files with timestamps
- Docker containerization
- UV package management
Environment Variables
- MISTRAL_API_KEY: Your Mistral AI API key
- OCR_DIR: Directory path for local file processing. Inside the container, this is always mapped to /data/ocr
Installation
Installing via Smithery
To install Mistral OCR for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @everaldo/mcp/mistral-crosswalk --client claude
Using Docker
1. Build the Docker image:
docker build -t mcp-mistral-ocr .
2. Run the container:
docker run -e MISTRAL_API_KEY=your_api_key -e OCR_DIR=/data/ocr -v /path/to/local/files:/data/ocr mcp-mistral-ocr
Local Development
1. Install UV package manager:
pip install uv
2. Create and activate virtual environment:
```bash
uv venv
source .venv/bin/activate # On Unix
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
