MCP servers · ai
Mistral MCP server
Open-weight AI models — chat, embeddings, code generation, function calling. Hosted by 0n3: 3 endpoints your AI can call with your own Mistral account, from Claude, ChatGPT, Cursor, Claude Code, Codex or Gemini CLI. One sign-in, one key per AI, a receipt for every call.
3 endpoints4 categoriesauth: api_keyhosted
What your AI can do with 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/embeddingsInstall in three steps
- Create a free account at 0n3.app and connect Mistral: paste a key or sign in through a door. It lands in your vault, encrypted.
- Open 0n3.app/install, pick your AI. A key is made for that AI alone; copy the line it gives you.
- Ask your AI: whoami. It answers with your connected services. Then ask it to chat completion in Mistral.
Install (user scope — every project)
claude mcp add --transport http --scope user 0n3 https://0n3.app/mcp --header "Authorization: Bearer <your 0n token>"
Connect Mistral to
Claude Code + MistralMCP server + skillClaude (desktop & claude.ai) + MistralconnectorChatGPT + Mistralconnector · GPT actionCodex CLI + MistralMCP serverGemini CLI + MistralMCP serverCursor + MistralMCP serverVS Code (Copilot) + MistralMCP serverWindsurf + MistralMCP server
More ai MCP servers
Questions
What can an AI do with the Mistral MCP server?
3 things: chat, models, embed, more. Every call runs with your own Mistral connection and lands on a receipt.
Do I need to run anything on my computer?
No. 0n3 is hosted. Connect Mistral once, install 0n3 into your AI with one line, done.
Where does my Mistral key go?
Into your 0n3 vault, encrypted, one record per connection. The AI never sees it.