Mistral OCR MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MISTRAL_API_KEY | No | Single Mistral API key (compatibility mode). | |
| MISTRAL_API_KEYS | No | Comma-, semicolon-, or newline-separated Mistral API keys for automatic fallback. | |
| MISTRAL_OCR_OUTPUT_DIR | No | Directory to save OCR Markdown outputs. Defaults to 'outputs/' next to server.py. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| set_api_keyC | Set one Mistral API key for this running MCP server. |
| set_api_keysC | Set one or more Mistral API keys for this running MCP server. |
| health_checkA | Check MCP configuration, key validity, output directory, and model name. |
| list_pagesB | Return basic local file information and PDF page count when available. |
| ocr_from_urlB | 从公开的文档或图片 URL 中提取 Markdown 文本。 |
| ocr_from_fileA | 从本地文件或图片中提取 Markdown 文本并以字符串形式返回。 |
| ocr_to_markdown_fileA | OCR 本地文件并将生成的 Markdown 保存至磁盘。 |
| ocr_url_to_markdown_fileA | OCR 公网 URL 指向的文件并将生成的 Markdown 保存至磁盘。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/uuina/mistral-ocr-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server