MCP servers · Ollama · connector · GPT action
Connect ChatGPT to Ollama
One line gives ChatGPT your Ollama account as tools: 8 endpoints, generate text, chat completion, create embedding, called with your own connection. No key in the prompt, a receipt for every call, revoke ChatGPT's access alone any time.
Three steps
- Create a free 0n3 account and connect Ollama. Paste a key or sign in; it lands in your vault, encrypted.
- Install 0n3 into ChatGPT. A custom connector in Developer mode, or an Action on a custom GPT from the OpenAPI spec.
- Ask ChatGPT: whoami. Then: "Generate in Ollama".
Custom connector (needs Developer mode)
- Settings → Connectors (or Apps) → Advanced → Developer mode on
- Create → name 0n3 · MCP server URL https://0n3.app/mcp · Authentication: OAuth
- Finish the sign-in with your 0n account
- Enable the connector in a chat and ask: "whoami"
ChatGPT connectors cannot send a static header, so 0n3 signs you in through its OAuth door (dynamic client registration is on).
The line above carries a placeholder; 0n3.app/install mints a real key named for ChatGPT and fills it in.
What ChatGPT can then do in Ollama
Generate text · Generate text completions with local models (Llama, Mistral, etc.)1
Generate
POST /api/generateChat completion · Multi-turn chat with local models1
Chat completion
POST /api/chatCreate embedding · Create text embeddings locally1
Create an embedding
POST /api/embedModels · List, pull, inspect, and delete local models4
List models
GET /api/tagsShow model
POST /api/showPull model
POST /api/pullDelete a model
DELETE /api/deleteMore · Everything else this app exposes.1
List running
GET /api/psOllama in other AI clients
Claude Code + OllamaMCP server + skillClaude (desktop & claude.ai) + OllamaconnectorCodex CLI + OllamaMCP serverGemini CLI + OllamaMCP serverCursor + OllamaMCP serverVS Code (Copilot) + OllamaMCP serverWindsurf + OllamaMCP server