MCP servers · Replicate · MCP server
Connect Codex CLI to Replicate
One line gives Codex CLI your Replicate account as tools: 8 endpoints, predictions, models, more, 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 Replicate. 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: "Create a prediction in Replicate".
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 Replicate
Predictions · Run model predictions4
Create a prediction
POST /v1/predictionsGet a prediction
GET /v1/predictions/{prediction_id}List predictions
GET /v1/predictionsCancel a prediction
POST /v1/predictions/{prediction_id}/cancelModels · Browse and search models3
Get a model
GET /v1/models/{owner}/{name}List model versions
GET /v1/models/{owner}/{name}/versionsSearch models
GET /v1/modelsMore · Everything else this app exposes.1
List collections
GET /v1/collectionsReplicate in other AI clients
Claude Code + ReplicateMCP server + skillClaude (desktop & claude.ai) + ReplicateconnectorChatGPT + Replicateconnector · GPT actionGemini CLI + ReplicateMCP serverCursor + ReplicateMCP serverVS Code (Copilot) + ReplicateMCP serverWindsurf + ReplicateMCP server