Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Swih/mistral-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/swih/mistral-mcp/mistral)<a href="https://agentmods.dev/mcp/swih/mistral-mcp/mistral"><img src="https://agentmods.dev/badge/mcp/swih/mistral-mcp/mistral/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/swih/mistral-mcp/mistral"><img src="https://agentmods.dev/badge/mcp/swih/mistral-mcp/mistral.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
mistral scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"mistral": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"MISTRAL_API_KEY": "${MISTRAL_API_KEY}"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +1 lines def69d892585
- 1mo ago First seen · 11 lines scan A dc04b181baba
mistral is an MCP server published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
prism-mcp
Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package. Needs 1…
mcp-failure-lab
A chaos-engineering and resilience-testing toolkit for Model Context Protocol servers. Runs locally from the mcp-failure-lab npm package.
ragmap
DEPRECATED: hosted backend discontinued; npm package deprecated. Formerly a retriever-MCP finder. Runs locally from the @khalidsaidi/ragmap-mcp npm package.
routara
MCP server for Routara — OpenAI-compatible LLM, image & video APIs at api.routara.ai. Runs locally from the routara-mcp npm package. Needs 1 environment variable to run.
routara-mcp
OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai). Runs locally from the routara-mcp npm package. Needs 2 environment variables to run.
samotpravil
MCP server "samotpravil" as configured in dkanster/samotpravil-api-mcp. Launched with .cursor/samotpravil-mcp.sh. Needs 4 environment variables to run.