Mistral MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MISTRAL_API_KEY | Yes | Your Mistral AI API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mistral_chat_completionB | Generate chat completions using Mistral AI models with function calling and vision support. |
| mistral_fim_completionC | Fill-in-the-Middle code completion using Codestral. |
| mistral_embeddingsB | Generate text embeddings for semantic search and similarity. |
| mistral_agents_completionC | Run completions using pre-configured Mistral Agents. |
| mistral_list_modelsB | List all available Mistral models with capabilities. |
| mistral_get_modelC | Get detailed information about a specific model. |
| mistral_delete_modelB | Delete a fine-tuned model (permanent). |
| mistral_list_filesC | List files uploaded to your Mistral account. |
| mistral_get_fileC | Get details about a specific file. |
| mistral_upload_fileA | Upload a file for fine-tuning, batch processing, or OCR. |
| mistral_delete_fileC | Delete a file from your account. |
| mistral_download_fileC | Download file contents. |
| mistral_get_signed_urlB | Get a temporary download URL for a file. |
| mistral_list_fine_tuning_jobsC | List fine-tuning jobs. |
| mistral_get_fine_tuning_jobB | Get details of a fine-tuning job. |
| mistral_create_fine_tuning_jobC | Create a new fine-tuning job. |
| mistral_cancel_fine_tuning_jobA | Cancel a running fine-tuning job. |
| mistral_start_fine_tuning_jobC | Start a validated fine-tuning job. |
| mistral_list_batch_jobsB | List batch processing jobs. |
| mistral_get_batch_jobC | Get details of a batch job. |
| mistral_create_batch_jobC | Create a new batch processing job. |
| mistral_cancel_batch_jobC | Cancel a batch job. |
| mistral_ocrB | Extract text from documents and images using OCR. |
| mistral_moderate_textC | Check text for safety issues. |
| mistral_moderate_chatB | Check chat messages for safety issues. |
| mistral_classify_textC | Classify text using a fine-tuned classifier. |
| mistral_transcribe_audioC | Transcribe audio files using Voxtral. |
| mistral_list_agentsC | List all Mistral agents. |
| mistral_get_agentC | Get details of an agent. |
| mistral_create_agentC | Create a new Mistral agent. |
| mistral_update_agentC | Update an existing agent. |
| mistral_delete_agentC | Delete an agent. |
| mistral_list_conversationsC | List all conversations. |
| mistral_get_conversationC | Get conversation details. |
| mistral_create_conversationC | Create a new conversation with an agent. |
| mistral_append_conversationC | Add messages to an existing conversation. |
| mistral_get_conversation_historyC | Get full conversation history. |
| mistral_delete_conversationC | Delete a conversation. |
| mistral_list_librariesB | List all document libraries. |
| mistral_get_libraryC | Get library details. |
| mistral_create_libraryC | Create a new document library. |
| mistral_update_libraryC | Update a library. |
| mistral_delete_libraryC | Delete a library. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 43 tools
Tools are mostly distinct, covering different resources (agents, conversations, libraries, files, jobs, models) and operations. Minor potential confusion exists between mistral_get_conversation and mistral_get_conversation_history, and between mistral_download_file and mistral_get_signed_url, but descriptions clarify the differences.
Consistent mistral_ prefix and snake_case throughout, with a predictable verb_noun structure for most tools. A few tools (e.g., mistral_embeddings, mistral_ocr, mistral_chat_completion) use noun-based names, slightly breaking the pattern but remaining readable.
With 43 tools, the set is heavy; while the breadth of the Mistral platform justifies many tools, it exceeds typical MCP server scope. Some consolidation might be possible (e.g., file download and signed URL), but each tool maps to a distinct API endpoint.
Covers CRUD for agents, conversations, libraries, files, and job management, plus core AI operations like completions, embeddings, OCR, moderation, and transcription. Notable gap: no tools to manage documents within libraries (add/remove/list documents), and some lifecycle operations (e.g., batch job deletion) are missing.