How to integrate Vercel MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Vercel Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Vercel to CrewAI using the Composio tool router. By the end, you'll have a working Vercel agent that can deploy latest changes to my project, add api key as production environment variable, check if mydomain.com is available for purchase, delete failed deployment by id through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Vercel account through Composio's Vercel MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Vercel connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Vercel
  • Build a conversational loop where your agent can execute Vercel operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Vercel MCP server, and what's possible with it?

The Vercel MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Vercel account. It provides structured and secure access to your Vercel projects and deployments, so your agent can perform actions like creating deployments, managing environment variables, handling edge configs, and checking domain statuses on your behalf.

  • Automated deployments and rollbacks: Easily instruct your agent to create new deployments or remove outdated ones, streamlining your release process without manual steps.
  • Environment variable management: Let your agent add or update sensitive configuration values across different environments, ensuring your projects are set up correctly before a deploy.
  • Edge configuration and token handling: Have your agent create new edge configs or generate secure tokens for read-only access, optimizing how your content is served globally.
  • Domain availability and pricing checks: Ask your agent to verify if a domain is available and fetch the latest price before you make a purchase decision.
  • Authentication token management: Enable your agent to create or revoke Vercel API tokens, giving you fine-grained control over programmatic access to your account.

Supported Tools & Triggers

Tools
Add Environment VariableTool to add an environment variable to a vercel project.
Check Cache Artifact ExistsTool to check if a cache artifact exists by its hash.
Check Domain AvailabilityTool to check if a domain is available for registration.
Check Domain PriceTool to check the price for a domain before purchase.
Create Auth TokenTool to create a new authentication token.
Create Edge ConfigTool to create a new edge config for a vercel project.
Create Edge Config TokenTool to create a new token for a specific edge config.
Create new deploymentTool to create a new deployment.
Delete Auth TokenTool to delete an authentication token.
Delete DeploymentTool to delete a specific deployment by its unique id.
Delete Edge Config TokensTool to delete tokens associated with a specific edge config.
Delete Environment VariableTool to delete a specific environment variable from a project.
Delete Vercel ProjectTool to delete a specific project by its id or name.
Deploy Edge FunctionDeploy edge functions to vercel.
Get Auth Token MetadataTool to retrieve metadata for an authentication token.
Get deployment detailsTool to retrieve detailed information about a specific deployment.
Get Deployment EventsTool to retrieve events related to a specific deployment.
Get Deployment LogsTool to retrieve logs for a specific vercel deployment.
Get Domain Transfer InfoTool to get information required to transfer a domain to vercel.
Get Edge ConfigTool to retrieve details of a specific edge config.
Get Edge Config ItemTool to retrieve a specific item within an edge config.
Get Edge Config TokenTool to retrieve details of a specific token associated with an edge config.
Get Vercel ProjectTool to retrieve information about a vercel project by id or name.
List Vercel AliasesTool to list all aliases for the authenticated user or team.
List All DeploymentsTool to list all deployments.
List Auth TokensTool to list authentication tokens.
List Deployment ChecksTool to retrieve a list of checks for a specific deployment.
List Edge Config ItemsTool to retrieve a list of items within a specific edge config.
List Edge ConfigsTool to list all edge configs.
List Edge Config TokensTool to retrieve a list of tokens for a specific edge config.
List Environment VariablesTool to list environment variables for a specific project.
List All TeamsTool to list all teams accessible to the authenticated user.
Update Edge ConfigTool to update an existing edge config.
Update Edge Config ItemsTool to update items within a specific edge config.
Update Vercel ProjectTool to update an existing project.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Vercel connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Vercel via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Vercel MCP URL

Create a Composio Tool Router session for Vercel

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["vercel"],
)
url = session.mcp.url
What's happening:
  • You create a Vercel only session through Composio
  • Composio returns an MCP HTTP URL that exposes Vercel tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Vercel Assistant",
    goal="Help users interact with Vercel through natural language commands",
    backstory=(
        "You are an expert assistant with access to Vercel tools. "
        "You can perform various Vercel operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Vercel MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Vercel operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Vercel related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_vercel_agent.py

Complete Code

Here's the complete code to get you started with Vercel and CrewAI:

python
# file: crewai_vercel_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Vercel session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["vercel"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Vercel assistant agent
    toolkit_agent = Agent(
        role="Vercel Assistant",
        goal="Help users interact with Vercel through natural language commands",
        backstory=(
            "You are an expert assistant with access to Vercel tools. "
            "You can perform various Vercel operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Vercel operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Vercel related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Vercel through Composio's Tool Router. The agent can perform Vercel operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Vercel MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Vercel MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Vercel MCP with Claude Agent SDK

Google ADK

Google ADK

Use Vercel MCP with Google ADK

LangChain

LangChain

Use Vercel MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Vercel MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Vercel MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Vercel MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Vercel MCP?

With a standalone Vercel MCP server, the agents and LLMs can only access a fixed set of Vercel tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Vercel and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Vercel tools.

Can I manage the permissions and scopes for Vercel while using Tool Router?

Yes, absolutely. You can configure which Vercel scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Vercel data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free