Plugin

mistral-mcp

Exposes the full Mistral AI API surface to Claude Code through a local MCP server: 22 tools (chat, streaming, embeddings, OCR, vision, Voxtral transcription and speech, Codestral FIM, agents, moderation, classification, files, batch), 2 live-fetched resources (model catalog, voice catalog), and 6 curated prompts. Ships 5 namespaced skills optimized for everyday workflows: code review via Codestral, Conventional Commits messages in French, meeting minutes from audio or text, B2B invoice reminders in French, and a meta-skill that routes tasks to the right Mistral model. Auto-installs the mistral-mcp npm package on first use; API key is stored in Claude Code's secrets storage and never written to settings.json.

• Published source
• Repository

Analysed

11 October 2026

Last observed

13 October 2026

What the code does

What does this mean?

These are capabilities our static analysis found in the latest published version. They describe what the code can do, not whether it is malicious: many tools need shell access or the network to do their job. Use them to decide what to check before installing.

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.