MCP servers · Mistral · MCP server
Connect Codex CLI to Mistral
One line gives Codex CLI your Mistral account as tools: 3 endpoints, chat, models, embed, called with your own connection. No key in the prompt, a receipt for every call, revoke Codex CLI's access alone any time.
Three steps
- Create a free 0n3 account and connect Mistral. Paste a key or sign in; it lands in your vault, encrypted.
- Install 0n3 into Codex CLI. OpenAI's terminal agent reads 0n3 over Streamable HTTP with a token from your environment.
- Ask Codex CLI: whoami. Then: "Chat completion in Mistral".
Put the token in your environment
export ON3_TOKEN="<your 0n token>"
Add it to your shell profile so Codex finds it next time.
The line above carries a placeholder; 0n3.app/install mints a real key named for Codex CLI and fills it in.
What Codex CLI can then do in Mistral
Chat · Chat completions1
Chat completion
POST /v1/chat/completionsModels · List available models1
List models
GET /v1/modelsEmbed · Text embeddings0
Text embeddings
More · Everything else this app exposes.1
Create an embedding
POST /v1/embeddingsMistral in other AI clients
Claude Code + MistralMCP server + skillClaude (desktop & claude.ai) + MistralconnectorChatGPT + Mistralconnector · GPT actionGemini CLI + MistralMCP serverCursor + MistralMCP serverVS Code (Copilot) + MistralMCP serverWindsurf + MistralMCP server