# mistral-mcp

> Use this tool when you need to access a comprehensive AI API surface with multiple tools and resources for tasks like chat, OCR, audio, and vision processing. It solves problems in areas such as text and image analysis, moderation, and classification, providing inputs through stdio or Str transport and outputting results in various formats. Use mistral-mcp in contexts where you require a wide range of AI capabilities, including embeddings, agents, and batch processing, with support for multiple languages and curated prompts.

Canonical page: https://skillsregistry.net/skills/swih-mistral-mcp  
JSON: https://api.skillsregistry.net/v1/skills/swih-mistral-mcp

## Description

mistral-mcp is a TypeScript MCP server (spec 2025-11-25) that exposes the full Mistral AI API surface:

22 tools: chat, OCR, audio (Voxtral), vision, agents, embeddings, moderation, classification, files, batch, sampling, FIM (Codestral), streaming
2 resources: mistral://models, mistral://voices
6 curated prompts (French + English) with MCP argument completion
Dual transport: stdio (default) + Str

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/adur5ll9bi)
- **Repository:** <https://github.com/Swih/mistral-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "swih-mistral-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/swih-mistral-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/swih-mistral-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt