# Render for AI agents. Managed auth, ready-made tools.

> Check services, review deploys, trigger new deploys and restart services in Render on behalf of each of your users.

- Page: https://www.agent200.com/connectors/render/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `render`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Render, through Agent200. In code: "render".
What it does: Check services, review deploys, trigger new deploys and restart services in Render on behalf of each of your users.
Page: https://www.agent200.com/connectors/render/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Render's own page, through the authorization link Agent200 returns. Never ask a user for a Render password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: render_list_services, render_get_service, render_list_deploys. Write tools: render_trigger_deploy, render_restart_service, render_suspend_service. Name "render" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/render/framework/claude/
   https://www.agent200.com/connectors/render/framework/chatgpt/
   https://www.agent200.com/connectors/render/framework/claude-code/
   https://www.agent200.com/connectors/render/framework/muse/
   https://www.agent200.com/connectors/render/framework/grok-bot/
   https://www.agent200.com/connectors/render/framework/openai-dots/
   https://www.agent200.com/connectors/render/framework/claude-duet/
   https://www.agent200.com/connectors/render/framework/hermes-agent/
   https://www.agent200.com/connectors/render/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Render connector, your agent works in each user's own Render workspace. It can list services, check their deploys, trigger a new deploy, restart a service or suspend one, using only the tools your project allows.

Render is a cloud platform for hosting web services, static sites, databases and background workers.

## Render tools

- **List services** (`render_list_services`, read): List the services in the user's workspace.
- **Get a service** (`render_get_service`, read): Get a service's settings and status.
- **List deploys** (`render_list_deploys`, read): List recent deploys of a service and their status.
- **Trigger a deploy** (`render_trigger_deploy`, write): Start a new deploy of a service.
- **Restart a service** (`render_restart_service`, write): Restart a running service.
- **Suspend a service** (`render_suspend_service`, write): Suspend a service so it stops running.

## Limits you can set

**Turn single tools on or off.** Let the agent read services and trigger deploys, and switch off `render_suspend_service` so it can never stop a service.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example deploys but not service restarts. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Render

Each end user authorizes their own Render account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Render account, once.
const connection = await agent200
  .user("user_123")
  .connect("render");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Render tools

Name the user, the model and the tools. The model decides which Render tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Did the last deploy of the API service succeed",
    tools: ["render"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, by connecting their own Render account. Each connection is their own.

**What access is requested.** The connection acts with that user's access to their Render workspace, such as reading services, triggering deploys or restarting a service. Users can revoke the connection later from their Render account settings.

## Example requests

- "Did the last deploy of the API service succeed"
- "Redeploy the web app"
- "Restart the background worker"

## Guides: Render with your AI framework

- [Render + Claude](https://www.agent200.com/connectors/render/framework/claude.md): Set up Render for Claude with Agent200, then check which tools are available to your agent.
- [Render + ChatGPT](https://www.agent200.com/connectors/render/framework/chatgpt.md): Set up Render for ChatGPT with Agent200, then check which tools are available to your agent.
- [Render + Claude Code](https://www.agent200.com/connectors/render/framework/claude-code.md): Set up Render for Claude Code with Agent200, then check which tools are available to your agent.
- [Render + Muse](https://www.agent200.com/connectors/render/framework/muse.md): Set up Render for Muse with Agent200, then check which tools are available to your agent.
- [Render + Grok Bot](https://www.agent200.com/connectors/render/framework/grok-bot.md): Set up Render for Grok Bot with Agent200, then check which tools are available to your agent.
- [Render + OpenAI Dots](https://www.agent200.com/connectors/render/framework/openai-dots.md): Set up Render for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Render + Claude Duet](https://www.agent200.com/connectors/render/framework/claude-duet.md): Set up Render for Claude Duet with Agent200, then check which tools are available to your agent.
- [Render + Hermes Agent](https://www.agent200.com/connectors/render/framework/hermes-agent.md): Set up Render for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Render + OpenClaw](https://www.agent200.com/connectors/render/framework/openclaw.md): Set up Render for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Render OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Render.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Render connection, never another user's. It cannot reach anything the user or Render has not authorized.

### Can I limit what my agent can do in Render?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/connectors/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/connectors/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/connectors/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/connectors/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
