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

> Check deployments, read build logs, manage environment variables and redeploy in your users' Vercel projects.

- Page: https://www.agent200.com/tools/vercel/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `vercel`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: Vercel, through Agent200. In code: "vercel".
What it does: Check deployments, read build logs, manage environment variables and redeploy in your users' Vercel projects.
Page: https://www.agent200.com/tools/vercel/

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 Vercel's own page, through the authorization link Agent200 returns. Never ask a user for a Vercel 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: vercel_list_projects, vercel_list_deployments, vercel_get_deployment, vercel_get_deployment_events, vercel_list_env_vars. Write tools: vercel_create_env_var, vercel_create_deployment. Name "vercel" 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/tools/vercel/framework/claude/
   https://www.agent200.com/tools/vercel/framework/chatgpt/
   https://www.agent200.com/tools/vercel/framework/claude-code/
   https://www.agent200.com/tools/vercel/framework/muse/
   https://www.agent200.com/tools/vercel/framework/grok-bot/
   https://www.agent200.com/tools/vercel/framework/openai-dots/
   https://www.agent200.com/tools/vercel/framework/claude-duet/
   https://www.agent200.com/tools/vercel/framework/hermes-agent/
   https://www.agent200.com/tools/vercel/framework/openclaw/

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

## About

With the Vercel connector, your agent checks on each user's own Vercel projects through Agent200: it lists deployments, reads build logs when one fails, manages environment variables and redeploys. Every user connects their own account through managed OAuth.

Vercel is a cloud platform for building and deploying web applications, with a preview deployment for every change and production deployments from Git.

## Vercel tools

- **List projects** (`vercel_list_projects`, read): List the projects in the connected account or team.
- **List deployments** (`vercel_list_deployments`, read): List recent deployments with their state and target.
- **Get a deployment** (`vercel_get_deployment`, read): Read a deployment's status, URL and Git source.
- **Get build logs** (`vercel_get_deployment_events`, read): Read the build output of a deployment.
- **List environment variables** (`vercel_list_env_vars`, read): List a project's environment variables and their targets.
- **Add an environment variable** (`vercel_create_env_var`, write): Add an environment variable to a project.
- **Redeploy** (`vercel_create_deployment`, write): Create a new deployment from an existing one.

## Limits you can set

**Turn single tools on or off.** Let your agent read deployments and logs, and switch off `vercel_create_deployment` and `vercel_create_env_var` if it should never change a project.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. 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 Vercel

Each end user authorizes their own Vercel 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 Vercel account, once.
const connection = await agent200
  .user("user_123")
  .connect("vercel");

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 Vercel tools

Name the user, the model and the tools. The model decides which Vercel 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: "Why did the last production deployment fail",
    tools: ["vercel"],
  });

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

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Vercel's own page. You never see or store their Vercel credentials.

**What access is requested.** The user picks the account or team to connect, and Vercel shows the permissions requested, such as reading deployments and managing environment variables.

## Example requests

- "Why did the last production deployment fail"
- "List this week's deployments for the marketing site"
- "Which environment variables are set for preview"
- "Redeploy the latest production build"

## Guides: Vercel with your AI framework

- [Vercel + Claude](https://www.agent200.com/tools/vercel/framework/claude.md): Connect Vercel to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Vercel + ChatGPT](https://www.agent200.com/tools/vercel/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds Vercel into your own agent with OpenAI's models and the Agent200 SDK.
- [Vercel + Claude Code](https://www.agent200.com/tools/vercel/framework/claude-code.md): Have Claude Code build a Vercel agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [Vercel + Muse](https://www.agent200.com/tools/vercel/framework/muse.md): Connect Vercel to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Vercel + Grok Bot](https://www.agent200.com/tools/vercel/framework/grok-bot.md): Connect Vercel to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Vercel + OpenAI Dots](https://www.agent200.com/tools/vercel/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Vercel agent with OpenAI's models and the Agent200 SDK.
- [Vercel + Claude Duet](https://www.agent200.com/tools/vercel/framework/claude-duet.md): Connect Vercel to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Vercel + Hermes Agent](https://www.agent200.com/tools/vercel/framework/hermes-agent.md): Connect Vercel to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Vercel + OpenClaw](https://www.agent200.com/tools/vercel/framework/openclaw.md): Connect Vercel to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the Vercel 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 Vercel.

### 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 Vercel connection, never another user's. It cannot reach anything the user or Vercel has not authorized.

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

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