Mistral MCP by usefulapi
Manage your Mistral platform — models, files, batch jobs, agents and RAG document libraries.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mistral": {
"url": "https://mistral.usefulapi.io/mcp"
}
}
}Remote endpoints
https://mistral.usefulapi.io/mcpstreamable-httpWhat it can do
Tool inventory
Tools (15)
🟢mistral_list_models
List every model available to your account — Mistral base models plus your fine-tuned models. Management API: GET /v1/models.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_model(model_id)
Retrieve details for a single model (base or fine-tuned). Management API: GET /v1/models/{model_id}.
Input Schema
{
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "The model id, e.g. mistral-large-latest or a fine-tuned model id."
}
},
"required": [
"model_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_list_files(page, page_size, purpose, search, source, ...)
List uploaded files belonging to your organization (fine-tune data, batch inputs/outputs, etc.). Management API: GET /v1/files.
Input Schema
{
"type": "object",
"properties": {
"page": {
"description": "Page number (0-indexed). Default 0.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"page_size": {
"description": "Files per page. Default 100.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"purpose": {
"description": "Filter by purpose, e.g. fine-tune, batch.",
"type": "string"
},
"search": {
"description": "Search files by name.",
"type": "string"
},
"source": {
"description": "Filter by source, e.g. upload, mistral.",
"type": "string"
},
"sample_type": {
"description": "Filter by sample type, e.g. instruct, batch_request.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_file(file_id)
Retrieve metadata about a specific uploaded file. Management API: GET /v1/files/{file_id}.
Input Schema
{
"type": "object",
"properties": {
"file_id": {
"type": "string",
"description": "The file id (UUID)."
}
},
"required": [
"file_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_file_url(file_id)
Get a temporary signed download URL for an uploaded file. Management API: GET /v1/files/{file_id}/url.
Input Schema
{
"type": "object",
"properties": {
"file_id": {
"type": "string",
"description": "The file id (UUID)."
}
},
"required": [
"file_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_list_batch_jobs(page, page_size, status, model, created_after, ...)
List batch inference jobs for your organization and user, with optional filters. Management API: GET /v1/batch/jobs.
Input Schema
{
"type": "object",
"properties": {
"page": {
"description": "Page number (0-indexed). Default 0.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"page_size": {
"description": "Jobs per page. Default 100.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"status": {
"description": "Filter by job status, e.g. QUEUED, RUNNING, SUCCESS, FAILED, CANCELLED.",
"type": "string"
},
"model": {
"description": "Filter by model name.",
"type": "string"
},
"created_after": {
"description": "ISO 8601 date-time; only jobs created after this time.",
"type": "string"
},
"created_by_me": {
"description": "If true, only jobs created by the current user. Default false.",
"type": "boolean"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_batch_job(job_id)
Retrieve details and status for a single batch job. Management API: GET /v1/batch/jobs/{job_id}.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"description": "The batch job id (UUID)."
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_list_agents(page, page_size)
List agent entities in your account, sorted by creation time. Management API: GET /v1/agents.
Input Schema
{
"type": "object",
"properties": {
"page": {
"description": "Page number (0-indexed). Default 0.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"page_size": {
"description": "Agents per page. Default 20.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_agent(agent_id)
Retrieve a single agent entity with its configuration. Management API: GET /v1/agents/{agent_id}.
Input Schema
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "The agent id."
}
},
"required": [
"agent_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_list_libraries(page_size, page_token, page, search)
List RAG document libraries you own or that have been shared with you. Management API: GET /v1/libraries.
Input Schema
{
"type": "object",
"properties": {
"page_size": {
"description": "Libraries per page (1-100). Default 100.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"page_token": {
"description": "Continuation cursor from a previous response's next_page_token.",
"type": "string"
},
"page": {
"description": "Deprecated offset page (use page_token). Default 0.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"search": {
"description": "Case-insensitive search on the library name.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_get_library(library_id)
Retrieve details about a single document library. Management API: GET /v1/libraries/{library_id}.
Input Schema
{
"type": "object",
"properties": {
"library_id": {
"type": "string",
"description": "The library id (UUID)."
}
},
"required": [
"library_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢mistral_list_library_documents(library_id, page_size, page, search)
List the documents uploaded to a given document library. Management API: GET /v1/libraries/{library_id}/documents.
Input Schema
{
"type": "object",
"properties": {
"library_id": {
"type": "string",
"description": "The library id (UUID)."
},
"page_size": {
"description": "Documents per page (1-100). Default 100.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"page": {
"description": "Page number (0-indexed). Default 0.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"search": {
"description": "Search documents by name.",
"type": "string"
}
},
"required": [
"library_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🔴mistral_create_agent(model, name, instructions, description, tools, ...)
Creates a Mistral Agent (additive configuration). Management API: POST /v1/agents. Requires model and name; instructions, tools, completion_args, description and handoffs are optional.
Input Schema
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model powering the agent, e.g. mistral-large-latest."
},
"name": {
"type": "string",
"description": "Human-readable agent name."
},
"instructions": {
"description": "System instruction prompt the agent follows.",
"type": "string"
},
"description": {
"description": "Free-text description of the agent.",
"type": "string"
},
"tools": {
"description": "Tools available to the agent (passthrough objects, e.g. {type:'web_search'}).",
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"completion_args": {
"description": "Completion arguments (temperature, top_p, etc.) as a passthrough object.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"handoffs": {
"description": "Agent ids this agent may hand off to.",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"model",
"name"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🔴mistral_cancel_batch_job(job_id)
Cancels a running Mistral batch job — stops processing and further billing for that job. Management API: POST /v1/batch/jobs/{job_id}/cancel.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"description": "The batch job id (UUID) to cancel."
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🔴mistral_delete_file(file_id)
Permanently deletes an uploaded file from Mistral. Destructive. Management API: DELETE /v1/files/{file_id}.
Input Schema
{
"type": "object",
"properties": {
"file_id": {
"type": "string",
"description": "The file id (UUID) to delete."
}
},
"required": [
"file_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Community
Evidence