# io.github.Swih/mistral-mcp (npm · mistral-mcp)

Mistral AI MCP server: chat, OCR, Voxtral audio, Codestral FIM, vision, agents, batch.

- Trust score: 63/100 (medium)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `mistral-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp.md), [page](https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp)

## Channel facts

- Registry: `npm`
- Package: `mistral-mcp`
- Version: `0.8.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (98 of 102), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (98 of 102), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 88 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2084 tokens (~189/item across 11 items; 8 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 49% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add swih-mistral-mcp -- npx -y mistral-mcp
```

### Codex

```bash
codex mcp add swih-mistral-mcp -- npx -y mistral-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "swih-mistral-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mistral-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add swih-mistral-mcp --command npx --arg -y --arg mistral-mcp
```

### Hermes

```yaml
mcp_servers:
  swih-mistral-mcp:
    command: "npx"
    args: ["-y", "mistral-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "swih-mistral-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mistral-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 63, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-07-31 (score 23, −8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 31, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 49)

First indexed and scored.

## MCP tools (8)

### `mistral_chat` (~328 tokens)

Mistral chat completion

Generate a chat completion using a Mistral model.

When to use:
\- Drafting French (or any European-language) content where Mistral shines.
\- Codestral for code-specific generation/review.
\- Ministral for cheap / low-latency classification.

Returns structured content with the assistant text and token usage.
Does NOT stream — use mistral_chat_stream for long outputs with progress updates.

Input parameters:

- `max_tokens` (integer)
- `messages` (array, required): Chat messages in role/content form.
- `model` (string): Mistral chat model alias. Allowed: mistral-large-latest, mistral-medium-latest, mistral-small-latest, ministral-3b-latest, ministral-8b-latest, ministral-14b-latest, magistral-medium-latest, magistra…
- `reasoning_effort` (string): Controls reasoning depth for Magistral models. 'high' enables full chain-of-thought; 'none' disables it. Ignored on non-reasoning models.
- `response_format`: Force a structured output: `{type:"json_object"}` for JSON mode, `{type:"json_schema", json_schema:{...}}` for strict schema mode.
- `seed` (integer): Random seed for deterministic sampling. Maps to Mistral's `random_seed`.
- `temperature` (number)
- `top_p` (number)

Output parameters:

- `finish_reason` (string)
- `model` (string)
- `reasoning_content` (string): Reasoning trace returned by Magistral models. Absent for non-reasoning models.
- `text` (string)
- `usage` (object)

### `codestral_fim` (~174 tokens)

Codestral fill-in-the-middle completion

Fill-in-the-middle code completion with Codestral.

Given `prompt` (code preceding the cursor) and `suffix` (code after the cursor),
Codestral writes the middle. Use for editor autocomplete scenarios, code-patching
agents, or structured refactors where you know the target boundaries.

Default stop tokens: [] — let the model decide. Override with `stop` if needed.

Input parameters:

- `max_tokens` (integer)
- `model` (string)
- `prompt` (string, required): Code preceding the cursor.
- `seed` (integer): Random seed for deterministic sampling. Maps to Mistral's `random_seed`.
- `stop` (array)
- `suffix` (string, required): Code after the cursor. Can be empty string.
- `temperature` (number)
- `top_p` (number)

Output parameters:

- `finish_reason` (string)
- `model` (string)
- `text` (string)
- `usage` (object)

### `mistral_vision` (~251 tokens)

Mistral multimodal chat (vision)

Chat completion with multimodal input: text + image_url parts.

Requires a vision-capable model. Accepted:
  \- pixtral-large-latest
  \- pixtral-12b-latest
  \- mistral-large-latest
  \- mistral-medium-latest
  \- mistral-small-latest

Each message's `content` is either a plain string (pure text) or an array of
parts `{ type: 'text', text }` / `{ type: 'image_url', imageUrl }`. The image URL
can be an https URL or a data: URI base64 payload.

Returns the assistant text + token usage. For non-visual requests, prefer `mistral_chat`.

Input parameters:

- `max_tokens` (integer)
- `messages` (array, required): Chat messages. Pure-text requests are accepted, but this tool is intended primarily for multimodal prompts containing image parts.
- `model` (string): Vision-capable Mistral model. Default: pixtral-large-latest.
- `seed` (integer): Random seed for deterministic sampling. Maps to Mistral's `random_seed`.
- `temperature` (number)
- `top_p` (number)

Output parameters:

- `finish_reason` (string)
- `model` (string)
- `text` (string)
- `usage` (object)

### `mistral_ocr` (~370 tokens)

Mistral OCR (document to markdown)

Run Mistral OCR on a PDF or image, returning structured markdown per page.

Input `document` is one of:
  \- { type: "document_url", documentUrl: "https://...pdf" }
  \- { type: "image_url", imageUrl: "https://..." | "data:image/..." }
  \- { type: "file", fileId: "<id-from-files-api>" }

Options:
  \- `pages`: array of 0-indexed page numbers or string like "0-5,7".
  \- `tableFormat`: 'markdown' (default) or 'html'.
  \- `extractHeader` / `extractFooter`: include page header/footer when present.
  \- `includeImageBase64`: embed extracted image bytes as base64 in the response.
  \- `document_annotation_format`: JSON schema for whole-document structured extraction.
  \- `bbox_annotation_format`: JSON schema for extracted image / bbox annotations.
  \- `confidence_scores_granularity`: 'page' or 'word'.

Returns `pages[].markdown` plus optional `pages[].hyperlinks`, `header`, `footer`,
\`images` bounding boxes, annotations, confidence scores, and `dimensions`.

Input parameters:

- `bbox_annotation_format` (object)
- `confidence_scores_granularity` (string)
- `document` (required)
- `document_annotation_format`
- `document_annotation_prompt` (string)
- `extractFooter` (boolean)
- `extractHeader` (boolean)
- `imageLimit` (integer)
- `imageMinSize` (integer)
- `includeImageBase64` (boolean)
- `model` (string): OCR model. Default: mistral-ocr-latest.
- `pages`
- `tableFormat` (string)

Output parameters:

- `annotations` (object)
- `document_annotation` (string)
- `model` (string)
- `pages` (array)
- `pages_count` (integer)
- `usage` (object)

### `voxtral_transcribe` (~281 tokens)

Voxtral speech-to-text

Transcribe an audio file to text using Mistral Voxtral.

Accepted models:
  \- voxtral-mini-latest
  \- voxtral-small-latest

Audio source is one of:
  \- { type: "file_url", fileUrl: "https://..." }  (public URL)
  \- { type: "file", fileId: "<id-from-files-api>" }

Options:
  \- `language`: ISO-639-1 hint (e.g. 'fr', 'en'). Boosts accuracy when known.
  \- `temperature`: sampling temperature.
  \- `diarize`: return per-speaker segments (default false).
  \- `timestampGranularities`: ['segment'] to return per-segment timestamps.
  \- `contextBias`: list of phrases/terms that should bias the decoder.

Returns plain `text`, detected `language`, optional `segments[]`, and token usage.

Input parameters:

- `audio` (required)
- `contextBias` (array)
- `diarize` (boolean)
- `language` (string): ISO-639-1 language hint (e.g. 'fr', 'en').
- `model` (string): STT model. Default: voxtral-mini-latest.
- `temperature` (number)
- `timestampGranularities` (array): Only 'segment' is currently supported.

Output parameters:

- `language` (string|null)
- `model` (string)
- `segments` (array)
- `text` (string)
- `usage` (object)

### `workflow_execute` (~223 tokens)

Execute a Mistral workflow

Start a Mistral Workflow execution.

\`workflowIdentifier` is the workflow name or ID (visible in mistral://workflows).
\`input` is a free-form JSON object matching the workflow's input schema.

Modes:
  \- waitForResult=false (default): returns immediately with execution_id and RUNNING status.
    Poll workflow_status to track completion.
  \- waitForResult=true: blocks until the workflow finishes and returns the result inline.
    Use timeoutSeconds (default 30) to cap the wait.

Use deploymentName to target a specific deployment slot when multiple are configured.

Input parameters:

- `deploymentName` (string): Target a specific deployment slot.
- `executionId` (string): Optional custom execution ID. Auto-generated if omitted.
- `input` (object): Input payload matching the workflow input schema.
- `timeoutSeconds` (integer): Max wait time when waitForResult=true. Default: 30.
- `waitForResult` (boolean): Block until completion and return result inline. Default: false.
- `workflowIdentifier` (string, required): Workflow name or ID.

Output parameters:

- `end_time` (string|null)
- `execution_id` (string)
- `result`
- `root_execution_id` (string)
- `start_time` (string)
- `status` (string|null)
- `sync` (boolean): true when waitForResult=true (result is inline).
- `total_duration_ms` (number|null)
- `workflow_name` (string)

### `workflow_status` (~96 tokens)

Get workflow execution status

Get the current state and result of a workflow execution.

Statuses: RUNNING | COMPLETED | FAILED | CANCELED | TERMINATED |
          CONTINUED_AS_NEW | TIMED_OUT | RETRYING_AFTER_ERROR

Poll until status is COMPLETED (or terminal) when waitForResult was false.
\`result` is populated once the workflow reaches a terminal state.

Input parameters:

- `executionId` (string, required): Execution ID from workflow_execute.

Output parameters:

- `end_time` (string|null)
- `execution_id` (string)
- `result`
- `root_execution_id` (string)
- `start_time` (string)
- `status` (string|null)
- `total_duration_ms` (number|null)
- `workflow_name` (string)

### `workflow_interact` (~207 tokens)

Signal, query, or update a running workflow

Send a signal to or run a query against a running workflow execution.

action=signal: fire-and-forget event; the workflow reacts asynchronously.
  \- `name`: signal name defined in the workflow.
  \- `input`: optional payload matching the signal's schema.

action=query: synchronous read of internal workflow state.
  \- `name`: query handler name defined in the workflow.
  \- `input`: optional parameters for the query.
  \- Returns `query_name` + `result` inline.

action=update: synchronous request to modify workflow state mid-execution.
  \- `name`: update handler name defined in the workflow.
  \- `input`: optional payload for the update.
  \- Returns `update_name` + `result` inline.

Input parameters:

- `action` (string, required): Interaction type.
- `executionId` (string, required): Target execution ID.
- `input` (object): Optional payload for the signal or query.
- `name` (string, required): Signal or query handler name.

Output parameters:

- `action` (string)
- `execution_id` (string)
- `message` (string): Confirmation message for signal actions.
- `query_name` (string)
- `result`: Query or update result payload.
- `update_name` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 23
- 2026-07-31: 23
- 2026-07-30: 31
- 2026-07-28: 49
- 2026-07-27: 49

## Links

- npm package: https://www.npmjs.com/package/mistral-mcp
- Socket report: https://socket.dev/npm/package/mistral-mcp
- Repository: https://github.com/Swih/mistral-mcp
- Changelog RSS feed: https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/swih-mistral-mcp/mistral-mcp