MCP servers · Render · connector · GPT action
Connect ChatGPT to Render
One line gives ChatGPT your Render account as tools: 7 endpoints, services, deploys, more, 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 Render. 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: "List services in Render".
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 Render
Services · Manage services6
List services
GET /servicesGet a service
GET /services/{serviceId}Create a service
POST /servicesList deploys
GET /services/{serviceId}/deploysCreate a deploy
POST /services/{serviceId}/deploysGet a deploy
GET /services/{serviceId}/deploys/{deployId}Deploys · Manage deploys0
Manage deploys
More · Everything else this app exposes.1
List env groups
GET /env-groupsRender in other AI clients
Claude Code + RenderMCP server + skillClaude (desktop & claude.ai) + RenderconnectorCodex CLI + RenderMCP serverGemini CLI + RenderMCP serverCursor + RenderMCP serverVS Code (Copilot) + RenderMCP serverWindsurf + RenderMCP server