# Vercel MCP

```json
{
  "name": "Vercel MCP",
  "slug": "vercel_mcp",
  "url": "https://composio.dev/toolkits/vercel_mcp",
  "markdown_url": "https://composio.dev/toolkits/vercel_mcp.md",
  "logo_url": "https://logos.composio.dev/api/vercel_mcp",
  "categories": [
    "developer tools & devops"
  ],
  "is_composio_managed": false,
  "updated_at": "2026-08-25T05:41:14.841Z"
}
```

![Vercel MCP logo](https://logos.composio.dev/api/vercel_mcp)

## Description

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Vercel MCP or direct API to search documentation, list projects, create deployments, and fetch deployment logs through natural language.

## Summary

Vercel MCP is Vercel's hosted MCP server for querying documentation and managing projects and deployments.
It provides a single endpoint to inspect deployments, view logs, and access project metadata.

## Categories

- developer tools & devops

## Toolkit Details

- Tools: 37

## Images

- Logo: https://logos.composio.dev/api/vercel_mcp

## Authentication

- **Dcr Oauth**
  - Type: `custom`
  - Description: Dcr Oauth authentication for Vercel MCP.
  - Setup:
    - Configure Dcr Oauth credentials for Vercel MCP.
    - Use the credentials when creating an auth config in Composio.

## Suggested Prompts

- List recent deployments for my project
- Get deployment logs for commit abc123
- Create a new deployment from branch

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `VERCEL_MCP_ADD_TOOLBAR_REACTION` | Add toolbar reaction | Add an emoji reaction to a message in a toolbar thread. |
| `VERCEL_MCP_BUY_ADDON` | Buy addon | Executes a Vercel add-on purchase (currently only "siem"), by integer quantity, previously quoted by get_purchase_quote — quoting first is REQUIRED; this tool rejects un-quoted calls. Get the quote, present it to the user for explicit approval (use a structured question tool such as AskUserQuestion when available), then call with confirm:true, the quote's idempotencyKey, and the same parameters. The team must be on the Flex plan. No price quote exists for add-ons; the charge is non-refundable. The quote returns required disclosures the assistant must relay before approval: the payment method (default card on file), that taxes/fees may apply on top of the price, the item terms (Flex plan required, billed on the next invoice), and a full-terms link. |
| `VERCEL_MCP_BUY_CREDITS` | Buy credits | Executes a prepaid Vercel credits purchase (v0, AI Gateway, or Vercel Agent) previously quoted by get_purchase_quote — quoting first is REQUIRED; this tool rejects un-quoted calls. Get the quote, present it to the user for explicit approval (use a structured question tool such as AskUserQuestion when available), then call with confirm:true, the quote's idempotencyKey, and the same parameters. When the user has not named an amount, offer quick-picks — $10, $25, $50, or $100 — or let them enter any custom amount ($1–$1000); do not just quote the range. Some credit types require a plan: Vercel Agent credits require the team to be on Vercel Pro (use buy_pro first), and v0 credits require a paid v0 plan (set up at v0.dev); AI Gateway credits have no plan prerequisite. If the required plan is missing the purchase is rejected (nothing is charged) with guidance. The charge is immediate and non-refundable. The quote returns required disclosures the assistant must relay before approval: the payment method (default card on file), that taxes/fees may apply on top of the base price, the item terms (credits expire in one year), and a full-terms link. |
| `VERCEL_MCP_BUY_DOMAIN` | Buy domain | Executes a single-domain registration previously quoted by get_purchase_quote (product:domain) — quoting first is REQUIRED; this tool rejects un-quoted calls. Get the quote, present it to the user for explicit approval (use a structured question tool such as AskUserQuestion when available), then call with confirm:true, the quote's idempotencyKey, the expectedPrice and years from the quote, and the full registrant contact to execute the non-refundable purchase. Vercel stores no reusable registrant profile, so contact details must be supplied each time. The quote returns required disclosures the assistant must relay before approval: the payment method (default card on file), that taxes/fees may apply on top of the price, the item terms (non-refundable), and, when auto-renew is on, the recurring-charge terms in disclosures.subscription (renews automatically each term at the then-current price until auto-renew is turned off), plus a full-terms link. |
| `VERCEL_MCP_BUY_PRO` | Buy pro | Executes a Vercel Pro upgrade previously quoted by get_purchase_quote — quoting first is REQUIRED; this tool rejects un-quoted calls. Get the quote, present it to the user for explicit approval (use a structured question tool such as AskUserQuestion when available), then call with confirm:true, the quote's idempotencyKey, and the same parameters. This starts RECURRING Pro billing immediately at the standard Pro price. The quote returns required disclosures the assistant must relay before approval: the payment method (default card on file), that taxes/fees may apply on top of the price, the subscription terms (recurring monthly charge, no trial, cancel anytime in billing settings), and a full-terms link. |
| `VERCEL_MCP_CHANGE_TOOLBAR_THREAD_RESOLVE_STATUS` | Change toolbar thread resolve status | Change the resolve status of a toolbar thread. Can be used to mark a thread as resolved or unresolve a previously resolved thread. |
| `VERCEL_MCP_CHECK_DOMAIN_AVAILABILITY_AND_PRICE` | Check domain availability and price | Check if domain names are available for purchase and get pricing information |
| `VERCEL_MCP_CREATE_GIT_PROJECT` | Create git project | Preferred when the intended source is pushed to an accessible remote repository's production branch. Create a Vercel project linked to that repository, or reuse the existing project already linked to it, to automatically deploy changes on every push. New projects have Vercel Authentication disabled. Creates a preview deployment from the production branch by default; do not ask for deployment confirmation. Use deploy_to_vercel only when no usable remote repository exists or the user explicitly requests a manual file deployment. This prevents new bare projects; it does not reconnect an existing unlinked project with the same name. |
| `VERCEL_MCP_DEPLOY_TO_VERCEL` | Deploy to vercel | Deploy files directly when no usable remote git repository exists or the user explicitly requests a manual file deployment. If the intended source is pushed to a repository's production branch, use create_git_project to automatically deploy changes on every push. Provide the file tree and an explicit target; Vercel auto-detects the framework and builds. |
| `VERCEL_MCP_EDIT_TOOLBAR_MESSAGE` | Edit toolbar message | Edit an existing message in a toolbar thread. |
| `VERCEL_MCP_GET_ACCESS_TO_VERCEL_URL` | Get access to vercel url | Creates a temporary shareable link that bypasses authentication for protected Vercel deployments. When you encounter a Vercel deployment URL (like https://myapp-abc123.vercel.app), you might receive a 403 (Forbidden) error when trying to access it. This tool generates a special URL with a '_vercel_share' parameter that allows temporary access without requiring login credentials. The shareable URL will expire in 23 hours. When you use the returned URL, that URL will redirect and set an auth cookie. If your fetch implementation does not support cookies, use the 'web_fetch_vercel_url' tool instead. |
| `VERCEL_MCP_GET_AGENT_RUN` | Get agent run | Get detailed metadata for a single Agent Run from an eve agent, including events, workflow metadata, usage, and subagent breakout data. Use list_agent_runs first if you need to discover a run ID. |
| `VERCEL_MCP_GET_AGENT_RUN_TRACE` | Get agent run trace | Get the trace for a single Agent Run from an eve agent, including turns, messages, reasoning, tool calls, token usage, and tool input/output when available. Use this for debugging exact agent behavior in production. |
| `VERCEL_MCP_GET_DEPLOYMENT` | Get deployment | Get a specific deployment by ID or URL. |
| `VERCEL_MCP_GET_DEPLOYMENT_BUILD_LOGS` | Get deployment build logs | Get the build logs for a deployment by ID or URL, to investigate why a build failed. Returns the most recent lines by default (where build errors appear). Use errorsOnly to see just the failing lines. Omit since and until for latest logs; use since to narrow the window and omit until when the end should be the current time. |
| `VERCEL_MCP_GET_DOMAIN_ORDER` | Get domain order | Get the status of a domain purchase order returned by buy_domain, to confirm whether the registration completed. |
| `VERCEL_MCP_GET_GIT_DEPLOYMENT_CONTEXT` | Get git deployment context | Lists every Vercel team authorized for the user, including its plan and linked Git projects. If linkedProjects is null, project listing failed for that team. |
| `VERCEL_MCP_GET_PROJECT` | Get project | Get a specific project in Vercel |
| `VERCEL_MCP_GET_PROJECT_DEPLOYMENT_PROTECTION` | Get project deployment protection | Get the effective password protection, Vercel Authentication, and Trusted IP settings for a Vercel project. Password values are never returned. |
| `VERCEL_MCP_GET_PURCHASE_QUOTE` | Get purchase quote | Read-only price quote for a Vercel purchase. NEVER charges. This is the ONLY way to obtain an idempotencyKey — the buy_* tools no longer quote and reject un-quoted calls, so this is the REQUIRED first step before any buy_* tool. It returns the cost (when Vercel exposes one) and an idempotencyKey to pass to the matching buy tool (buy_credits, buy_domain, buy_addon, buy_pro) with confirm:true within 5 minutes to execute the charge. Present the quote to the user for explicit approval (use a structured question tool such as AskUserQuestion when available) before confirming. Products with no API price (add-ons, Pro) return a priceNote and billing URL instead of a number. Every quote includes a disclosures object the assistant must relay to the user before approval: the payment method (default card on file), that taxes/fees may apply on top of the base price, the item terms, and a link to the full terms. |
| `VERCEL_MCP_GET_RUNTIME_ERRORS` | Get runtime errors | Get grouped runtime error clusters for a project (error name, occurrence count, affected routes, sample messages, first/last seen). Use this first to answer "why is production erroring" — it reads a pre-aggregated table and does not time out. For recent windows, pass since like "24h" or "7d" and omit until; until is only needed for historical end times. Max 7-day range. |
| `VERCEL_MCP_GET_RUNTIME_LOGS` | Get runtime logs | Get runtime logs for a project or deployment. Runtime logs show application output (console.log, errors, etc.) from serverless functions and edge functions during execution. Supports filtering by environment, log level, status code, source, time range, and full-text search. For recent windows, pass since like "30m" or "24h" and omit until; until is only needed for historical end times. For wide time ranges, scope to a deploymentId for speed, or use group_by to get counts instead of individual lines. To investigate production errors specifically, prefer get_runtime_errors. |
| `VERCEL_MCP_GET_TOOLBAR_THREAD` | Get toolbar thread | Get a specific toolbar thread by ID, including all messages and context. |
| `VERCEL_MCP_GET_WEB_ANALYTICS` | Get web analytics | Query Web Analytics for a Vercel project. Count mode returns total visitors and pageviews (or custom event count). Aggregate mode groups results over time or by dimensions such as route, requestPath, country, referrerHostname, deviceType, browserName, eventName, flags/, or eventData/. Web Analytics must be enabled for the project. |
| `VERCEL_MCP_IMPORT_CLAUDE_DESIGN_FROM_URL` | Import-claude-design-from-url | Import a design into Vercel from a publicly fetchable URL. The file is a self-contained HTML bundle with all images, fonts, and styles inlined. |
| `VERCEL_MCP_LIST_AGENT_RUN_PROJECTS` | List agent run projects | List projects in a Vercel team that have Agent Runs observability data for agents built with the eve framework, with run counts and average duration rollups. Use this to discover which projects have eve agent activity before drilling into a project. |
| `VERCEL_MCP_LIST_AGENT_RUNS` | List agent runs | List Agent Runs for a Vercel project. Agent Runs are the observability layer for agents built with the eve framework. The response includes summaries, status, model, trigger, token usage, time series, and pagination metadata. Use this to find recent or matching production eve agent runs before fetching detail or trace data. |
| `VERCEL_MCP_LIST_DEPLOYMENTS` | List deployments | List all deployments for a project |
| `VERCEL_MCP_LIST_PROJECTS` | List projects | List all Vercel projects for a user (with a max of 50). Use this to help discover the Project ID of the project that the user is working on. |
| `VERCEL_MCP_LIST_TEAMS` | List teams | List the user's teams. Use this to help discover the Team ID of the teams that the user is part of. |
| `VERCEL_MCP_LIST_TOOLBAR_THREADS` | List toolbar threads | List Vercel toolbar comment threads for a team. Returns unresolved threads by default. Use this to see feedback, comments, or discussions on deployments and previews. |
| `VERCEL_MCP_PAUSE_PROJECT` | Pause project | Pause a Vercel project. Its production deployment will stop serving traffic and return 503 DEPLOYMENT_PAUSED until the project is unpaused. |
| `VERCEL_MCP_REPLY_TO_TOOLBAR_THREAD` | Reply to toolbar thread | Add a reply message to an existing toolbar thread. |
| `VERCEL_MCP_SEARCH_VERCEL_DOCUMENTATION` | Search vercel documentation | Search the Vercel documentation. Use this tool to answer any questions about Vercel’s platform, features, and best practices, including: - Core Concepts: Projects, Deployments, Git Integration, Preview Deployments, Environments - Frontend & Frameworks: Next.js, SvelteKit, Nuxt, Astro, Remix, frameworks configuration and optimization - APIs: REST API, Vercel SDK, Build Output API - Compute: Fluid Compute, Functions, Routing Middleware, Cron Jobs, OG Image Generation, Sandbox, Data Cache - AI: Vercel AI SDK, AI Gateway, MCP, v0 - Performance & Delivery: Edge Network, Caching, CDN, Image Optimization, Headers, Redirects, Rewrites - Pricing: Plans, Spend Management, Billing - Security: Audit Logs, Firewall, Bot Management, BotID, OIDC, RBAC, Secure Compute, 2FA - Storage: Blog, Edge Config |
| `VERCEL_MCP_UNPAUSE_PROJECT` | Unpause project | Unpause a Vercel project so its production deployment can resume serving traffic and consuming metered resources. |
| `VERCEL_MCP_UPDATE_PROJECT_DEPLOYMENT_PROTECTION` | Update project deployment protection | Partially update password protection, Vercel Authentication, and Trusted IPs for a Vercel project. Omitted settings are preserved. Availability depends on the Vercel team plan and caller permissions. |
| `VERCEL_MCP_WEB_FETCH_VERCEL_URL` | Web fetch vercel url | Fetches a Vercel deployment URL and returns the response. This is useful if another web fetch tool returns 401 (Unauthorized) or 403 (Forbidden) for a Vercel URL. Supports accessing deployments protected with Vercel Authentication which the user of this MCP server has access to. |

## Supported Triggers

None listed.

## Installation and MCP Setup

### Path 1: SDK Installation

#### Path 1, Step 1: Install Composio

Install the Composio SDK
```python
pip install composio_openai
```

```typescript
npm install @composio/openai
```

#### Path 1, Step 2: Initialize Composio and Create Tool Router Session

Import and initialize Composio client, then create a Tool Router session
```python
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
openai = OpenAI()
session = composio.create(user_id='your-user-id')
```

```typescript
import OpenAI from 'openai';
import { Composio } from '@composio/core';
import { OpenAIResponsesProvider } from '@composio/openai';

const composio = new Composio({
  provider: new OpenAIResponsesProvider(),
});
const openai = new OpenAI({});
const session = await composio.create('your-user-id');
```

#### Path 1, Step 3: Execute Vercel MCP Tools via Tool Router with Your Agent

Get tools from Tool Router session and execute Vercel MCP actions with your Agent
```python
tools = session.tools
response = openai.responses.create(
  model='gpt-4.1',
  tools=tools,
  input=[{
    'role': 'user',
    'content': 'YOUR_SPECIFIC_PROMPT_HERE'
  }]
)
result = composio.provider.handle_tool_calls(
  response=response,
  user_id='your-user-id'
)
print(result)
```

```typescript
const tools = session.tools;
const response = await openai.responses.create({
  model: 'gpt-4.1',
  tools: tools,
  input: [{
    role: 'user',
    content: 'YOUR_SPECIFIC_PROMPT_HERE'
  }],
});
const result = await composio.provider.handleToolCalls(
  'your-user-id',
  response.output
);
console.log(result);
```

### Path 2: MCP Server Setup

#### Path 2, Step 1: Install Composio

Install the Composio SDK for Python or TypeScript
```python
pip install composio claude-agent-sdk
```

```typescript
npm install @composio/core ai @ai-sdk/openai @ai-sdk/mcp
```

#### Path 2, Step 2: Initialize Client and Create Tool Router Session

Import and initialize the Composio client, then create a Tool Router session for Vercel MCP
```python
from composio import Composio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions

composio = Composio(api_key='your-composio-api-key')
session = composio.create(user_id='your-user-id')
url = session.mcp.url
```

```typescript
import { Composio } from '@composio/core';

const composio = new Composio({ apiKey: 'your-api-key' });
const session = await composio.create('your-user-id');
console.log(`Tool Router session created: ${session.mcp.url}`);
```

#### Path 2, Step 3: Connect to AI Agent

Use the MCP server with your AI agent (Anthropic Claude or Mastra)
```python
import asyncio

options = ClaudeAgentOptions(
    permission_mode='bypassPermissions',
    mcp_servers={
        'tool_router': {
            'type': 'http',
            'url': url,
            'headers': {
                'x-api-key': 'your-composio-api-key'
            }
        }
    },
    system_prompt='You are a helpful assistant with access to Vercel MCP tools.',
    max_turns=10
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query('YOUR_SPECIFIC_PROMPT_HERE')
        async for message in client.receive_response():
            if hasattr(message, 'content'):
                for block in message.content:
                    if hasattr(block, 'text'):
                        print(block.text)

asyncio.run(main())
```

```typescript
import { openai } from '@ai-sdk/openai';
import { experimental_createMCPClient as createMCPClient } from '@ai-sdk/mcp';
import { generateText } from 'ai';

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: session.mcp.url,
    headers: {
      'x-api-key': 'your-composio-api-key',
    },
  },
});

const tools = await client.tools();
const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  messages: [{
    role: 'user',
    content: 'YOUR_SPECIFIC_PROMPT_HERE'
  }],
  maxSteps: 5,
});

console.log(`Agent: ${text}`);
```

## Why Use Composio?

### 1. AI Native Vercel MCP Integration

- Supports both Vercel MCP and direct API based integrations
- Structured, LLM-friendly schemas for reliable tool execution
- Rich coverage for reading, writing, and querying your Vercel MCP data

### 2. Managed Auth

- Built-in OAuth handling with automatic token refresh and rotation
- Central place to manage, scope, and revoke Vercel MCP access
- Per user and per environment credentials instead of hard-coded keys

### 3. Agent Optimized Design

- Tools are tuned using real error and success rates to improve reliability over time
- Comprehensive execution logs so you always know what ran, when, and on whose behalf

### 4. Enterprise Grade Security

- Fine-grained RBAC so you control which agents and users can access Vercel MCP
- Scoped, least privilege access to Vercel MCP resources
- Full audit trail of agent actions to support review and compliance

## Use Vercel MCP with any AI Agent Framework

Choose a framework you want to connect Vercel MCP with:

- [ChatGPT Work](https://composio.dev/toolkits/vercel_mcp/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/vercel_mcp/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/vercel_mcp/framework/hermes-agent)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [1password](https://composio.dev/toolkits/_1password) - 1Password is a password manager and digital vault for storing logins, secrets, notes, and secure documents. It helps individuals and teams protect credentials, share access safely, and reduce password risk.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Authyo](https://composio.dev/toolkits/authyo) - Authyo is a REST API service for passwordless authentication, OTP verification, session management, and transactional notifications. Use it to add secure login flows and user verification without building auth infrastructure from scratch.
- [AWS Marketplace MCP](https://composio.dev/toolkits/aws_marketplace_mcp) - AWS Marketplace MCP provides MCP access to AWS Marketplace's cloud software, data, and services catalog. Use it to discover, compare, and evaluate 30K+ AWS Marketplace listings faster.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.

## Frequently Asked Questions

### Do I need my own developer credentials to use Vercel MCP with Composio?

Yes, Vercel MCP requires you to configure your own Dcr Oauth credentials. Once set up, Composio handles secure credential storage and management for you.

### Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. [Learn more](https://docs.composio.dev/tool-router/overview).

### Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. [Learn more](https://trust.composio.dev).

### What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)