8 tools from the Mistral MCP Server, categorised by risk level.
View the Mistral policy →voxtral_transcribe Transcribe an audio file to text using Mistral Voxtral.
Accepted models:
- voxtral-mini-latest
- voxtral-small-latest
Audio source is one of:... workflow_status Get the current state and result of a workflow execution.
Statuses: RUNNING | COMPLETED | FAILED | CANCELED | TERMINATED |
CONTINUED_AS_... codestral_fim Fill-in-the-middle code completion with Codestral.
Given `prompt` (code preceding the cursor) and `suffix` (code after the cursor),
Codestral writ... mistral_chat Generate a chat completion using a Mistral model.
When to use:
- Drafting French (or any European-language) content where Mistral shines.
- Codest... mistral_ocr Run Mistral OCR on a PDF or image, returning structured markdown per page.
Input `document` is one of:
- { type: "document_url", documentUrl: "h... mistral_vision Chat completion with multimodal input: text + image_url parts.
Requires a vision-capable model. Accepted:
- pixtral-large-latest
- pixtral-12b... workflow_execute Start a Mistral Workflow execution.
`workflowIdentifier` is the workflow name or ID (visible in mistral://workflows).
`input` is a free-form JSON ... workflow_interact Send a signal to or run a query against a running workflow execution.
action=signal: fire-and-forget event; the workflow reacts asynchronously.
... The Mistral MCP server exposes 8 tools across 2 categories: Read, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Mistral server.
Mistral tools are categorised as Read (2), Execute (6). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.