mistral-mcp-openclaw — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mistral-mcp-openclaw (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Created by the maintainer of mistral-mcp. This is a community skill, not an official OpenClaw or Mistral integration.Use this skill when you want OpenClaw to access Mistral capabilities beyond the built-in chat/model routing provider:
workflow_execute / status / interact)OpenClaw already includes a built-in Mistral provider for chat. This skill is for tool-level MCP access alongside that provider.
MISTRAL_API_KEY in your environmentmistral-mcp installed from npmInstall the MCP server package globally:
npm install -g mistral-mcpSet your Mistral API key in your shell environment:
export MISTRAL_API_KEY="sk-..."Register the stdio MCP server in OpenClaw:
openclaw mcp set mistral '{"command":"mistral-mcp","env":{"MISTRAL_API_KEY":"${MISTRAL_API_KEY}"}}'Check the saved definition:
openclaw mcp show mistral --jsonUse this skill for workflows where the agent needs a Mistral-specific tool, not just a chat model:
mistral-mcp package before installing it if you operate in a sensitive workspace. Source: https://github.com/Swih/mistral-mcp.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.