mistral-mcp: Instructions file for Claude Code

CLAUDE.md

mistral-mcp CLAUDE.md is an instructions file for Claude Code from Swih/mistral-mcp. It costs 3,342 tokens per session, scanned A, original, MIT.

Repository instructions for building mistral-mcp, a server that lets coding tools and other applications use Mistral's artificial-intelligence API through MCP, a shared tool-connection standard.

In plain words
What is it for?
It is for maintaining the server, its standard-input and web connections, and its registered tools, resources, and prompts.
Why use it?
It records the required protocol versions, server structure, and compatibility rules so changes do not break supported clients.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Swih/mistral-mcp's own configuration. It tells Claude Code how to work on mistral-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mistral-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Swih/mistral-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Swih/mistral-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Swih/mistral-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for mistral-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/swih/mistral-mcp/claude-md.svg)](https://agentmods.dev/instructions/swih/mistral-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/swih/mistral-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/swih/mistral-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,342 This file is loaded in full into every session.
When invoked 3,342 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03342 $0.03342
Opus 5 $0.01671 $0.01671
Sonnet 5 $0.00668 $0.00668
Haiku 4.5 $0.00334 $0.00334

Measured 8d ago against content hash 158f17a5e632, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mistral-mcp CLAUDE.md 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 8d 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.

CLAUDE.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mistral-mcp

Instructions de travail pour Claude (Opus 4.7) sur ce repo. Objectif : produire un MCP server Mistral feature-complete et spec-compliant qui peut dormir 6–12 mois sans régression.


1. Identité du projet

  • Nom : mistral-mcp (npm + github.com/Swih/mistral-mcp)
  • Rôle : serveur MCP stdio + Streamable HTTP wrappant l'API Mistral pour clients MCP (Claude Code, Cursor, Zed, Windsurf, Claude Desktop, ChatGPT Apps).
  • Versions en vigueur :
    • MCP spec : 2026-07-28, plus le handshake 2025 servi depuis les mêmes enregistrements. Le second n'est pas de la dette : c'est ce que parlent quasiment tous les clients diffusés. Toute évolution doit rester servable aux deux ères — test/stdio/protocol-eras.test.ts le vérifie.
    • SDK MCP : @modelcontextprotocol/server@^2.0.0toujours via la high-level API McpServer + registerTool/Resource/Prompt. Ne jamais descendre au low-level Server.
      • stdio et HTTP prennent une factory, jamais une instance : serveStdio(factory, { legacy: "serve" }) et createMcpHandler(factory, { legacy: "stateless" }). C'est le SDK qui décide de l'ère.
      • @modelcontextprotocol/sdk@^1.30.0 reste en devDependency : c'est le client de l'ère 2025 utilisé pour tester la compat, rien d'autre ne doit l'importer.
    • SDK Mistral : @mistralai/mistralai@^2.6.4 (Speakeasy-generated). Retry config obligatoire.
    • zod : ^4.2.0 (plancher imposé par le SDK v2). Attention : .default() porte sur le type de sortie en zod 4 — pour un objet dont les champs ont leurs propres defaults, c'est .prefault({}).
    • Node : >=20, TypeScript strict.

2. Règles dures (ne pas transgresser)

  1. Zéro claim non-vérifiable. Si une feature n'est pas shippée dans ce repo et testée, elle n'existe pas dans le README, la doc, le CHANGELOG. Pas de "coming soon", pas de roadmap aspirationnelle vendue comme acquise.
  2. Langues : FR + EN uniquement. Prompts, docs, commentaires, messages d'erreur. Aucune autre langue. Si on trouve de l'espagnol/allemand/etc. dans le code, on strippe.
  3. Spec-compliance >>> ergonomie. Si la spec MCP dit "include outputSchema" ou "annotations are REQUIRED for read/write hints", on fait. Toujours.
  4. Chaque tool renvoie content[] ET structuredContent. content[] = fallback lisible pour clients pré-2025-06-18. structuredContent = payload JSON strict conforme à outputSchema. Jamais l'un sans l'autre.
  5. Chaque tool déclare annotations : title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Pour un wrapper API externe, openWorldHint=true quasi toujours.
  6. Erreurs API → { content: [text], isError: true }, jamais throw. Le LLM appelant doit pouvoir self-correct.
  7. Les inputs zod sont la source de vérité. Jamais de cast as any, jamais de z.any(). Si un type Mistral n'est pas exporté, on le reconstruit avec zod, on ne "fait confiance".
  8. Le retry config est non-négociable : backoff strategy, initialInterval: 500, maxInterval: 5000, exponent: 2, maxElapsedTime: 30000, retryConnectionErrors: true, timeoutMs: 60000.
  9. Pas d'env var autre que MISTRAL_API_KEY sans justification. L'API key est lue UNE fois dans src/index.ts.
  10. Pas de dépendance runtime ajoutée sans approbation explicite. Les seules deps runtime acceptées : @modelcontextprotocol/server, @mistralai/mistralai, zod. Point final. C'est pourquoi l'adaptateur node:http ↔ web-standard est écrit à la main dans transport.ts plutôt que pris chez @modelcontextprotocol/node, qui traîne @hono/node-server pour quarante lignes.

Read the full file on GitHub · 197 lines

Changes

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.

  1. 8d ago First seen · 197 lines · 3,342 tokens per session scan A 158f17a5e632

Subscribe to this mod's changes

mistral-mcp CLAUDE.md is an instructions file published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 10d ago), licensed MIT. It adds 3,342 tokens to every session, about $0.0167 per session on Opus 5. 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens