MCP servers · OpenAI · MCP server
Connect Gemini CLI to OpenAI
One line gives Gemini CLI your OpenAI account as tools: 4 endpoints, generate image, create embedding, text to speech, called with your own connection. No key in the prompt, a receipt for every call, revoke Gemini CLI's access alone any time.
Three steps
- Create a free 0n3 account and connect OpenAI. Paste a key or sign in; it lands in your vault, encrypted.
- Install 0n3 into Gemini CLI. Google's terminal agent. One command at user scope.
- Ask Gemini CLI: whoami. Then: "Create an image in OpenAI".
Install (user scope)
gemini mcp add --scope user --transport http 0n3 https://0n3.app/mcp -H "Authorization: Bearer <your 0n token>"
The line above carries a placeholder; 0n3.app/install mints a real key named for Gemini CLI and fills it in.
What Gemini CLI can then do in OpenAI
Generate image · Generate images with DALL-E1
Create an image
POST /images/generationsCreate embedding · Create text embeddings1
Create an embedding
POST /embeddingsText to speech · Convert text to speech1
Text to speech
POST /audio/speechGenerate text · Generate text completions0
Generate text completions
More · Everything else this app exposes.1
Chat completion
POST /chat/completionsOpenAI in other AI clients
Claude Code + OpenAIMCP server + skillClaude (desktop & claude.ai) + OpenAIconnectorChatGPT + OpenAIconnector · GPT actionCodex CLI + OpenAIMCP serverCursor + OpenAIMCP serverVS Code (Copilot) + OpenAIMCP serverWindsurf + OpenAIMCP server