MCP servers · Ollama · MCP server
Connect Codex CLI to Ollama
One line gives Codex CLI 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 Codex CLI'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 Codex CLI. OpenAI's terminal agent reads 0n3 over Streamable HTTP with a token from your environment.
- Ask Codex CLI: whoami. Then: "Generate in Ollama".
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 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) + OllamaconnectorChatGPT + Ollamaconnector · GPT actionGemini CLI + OllamaMCP serverCursor + OllamaMCP serverVS Code (Copilot) + OllamaMCP serverWindsurf + OllamaMCP server