How to integrate Vercel MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Vercel logo
AutoGen logo
divider

Introduction

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

This guide will help you understand how to give your AutoGen 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.

Also integrate Vercel with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Vercel
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Vercel tools
  • Run a live chat loop where you ask the agent to perform Vercel operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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  • Automated deployments and rollbacks: Easily instruct your agent to create new deployments or remove outdated ones, streamlining your release process without manual steps.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.
Add Domain to ProjectTool to attach a custom domain to a Vercel project.
Assign Alias to DeploymentTool to assign an alias to a specific Vercel deployment.
Batch Remove Project Environment VariablesTool to batch remove environment variables from a Vercel project.
Buy DomainsTool to purchase multiple domains through Vercel's domain registrar.
Buy Single DomainTool to purchase a domain through Vercel's domain registrar.
Check 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 PriceCheck pricing for a domain including purchase, renewal, and transfer costs.
Create Auth TokenTool to create a new authentication token.
Create DNS RecordTool to create a new DNS record for a domain.
Create Edge ConfigCreates a new Edge Config for storing key-value data at the edge.
Create Edge Config TokenCreate a read access token for a specific Edge Config.
Create new deploymentTool to create a new deployment.
Create or Transfer DomainTool to add an existing domain to the Vercel platform.
Create Vercel Project (v2)Tool to create a new Vercel project with comprehensive configuration options.
Create Project Transfer RequestTool to create a project transfer request.
Create Shared Environment VariableTool to create one or more shared environment variables in Vercel.
Create WebhookTool to create a webhook for receiving notifications about Vercel events.
Dangerously Delete By Source ImagesTool to dangerously delete edge cache by source image URLs.
Dangerously Delete Cache By TagsTool to dangerously delete edge cache by tags.
Delete Vercel AliasTool to delete an alias from Vercel.
Delete Auth TokenTool to delete an authentication token.
Purge All Data CacheTool to purge all data cache entries for a specific project.
Delete Deployment (V2)Permanently delete a Vercel deployment by its ID or URL.
Delete DNS RecordTool to delete a DNS record from a domain.
Delete DomainTool to remove a domain by name from Vercel.
Delete Edge ConfigTool to delete an Edge Config by its unique identifier.
Delete Edge Config Tokens (v2)Tool to delete one or more Edge Config tokens.
Delete Vercel Project (v2)Tool to delete a Vercel project by ID or name.
Remove Project Environment VariableTool to remove an environment variable from a Vercel project.
Delete Rolling Release ConfigurationTool to delete rolling release configuration for a project.
Delete Shared Env VariableTool to delete one or more shared environment variables.
Delete Vercel WebhookDelete a webhook by its unique ID to stop receiving event notifications.
Download Cache ArtifactDownload a cache artifact from Vercel's Remote Cache by its hash.
Edit Project Environment VariableTool to edit an environment variable in a Vercel project.
Filter Project Environment VariablesTool to retrieve environment variables of a Vercel project by id or name.
Get Active Attack StatusTool to read active attack data from Vercel Firewall for a specific project.
Get Vercel AliasTool to retrieve information about a Vercel alias by ID or alias name.
Query Artifact InformationTool to query information about artifacts by their hashes.
Get Auth Token MetadataTool to retrieve metadata for an authentication token.
Get Authenticated UserTool to get the authenticated user's profile.
Get Bulk Domain AvailabilityTool to check availability for multiple domains at once.
Get Remote Caching StatusTool to get the status of Remote Caching for the principal.
Get SSL/TLS CertificatesTool to retrieve SSL/TLS certificates for the authenticated user or team.
Get Integration ConfigurationsTool to get configurations for the authenticated user or team.
Get Contact Info SchemaTool to retrieve the contact information schema for a domain's top-level domain (TLD).
Get Deployment by ID or URLTool to get a deployment by ID or URL.
Get Deployment EventsTool to get deployment events for a specific Vercel deployment by ID or URL.
Get Deployment File ContentsRetrieve the contents of a specific file from a Vercel deployment.
Get Deployment Runtime LogsTool to retrieve runtime logs for a specific Vercel deployment by project and deployment ID.
Get DeploymentsTool to list deployments from Vercel.
Get Domain InformationTool to retrieve complete information for a single domain.
Get Domain ConfigurationTool to get a domain's configuration details from Vercel.
Get Domain Transfer InfoTool to get information required to transfer a domain to Vercel.
Get All DrainsTool to retrieve a list of all drains.
Get Edge ConfigTool to retrieve detailed information about a specific Edge Config by ID.
Get Edge Config BackupTool to retrieve a specific backup version of an Edge Config.
Get Edge Config ItemTool to retrieve a specific item within an Edge Config.
Get Edge Config SchemaTool to retrieve the JSON schema of a specific Edge Config.
Get Edge Config TokenTool to retrieve details of a specific token associated with an Edge Config.
Get Firewall ConfigurationTool to retrieve firewall configuration for a Vercel project.
List Git NamespacesTool to list Git namespaces (organizations/users) by provider.
Find Project by ID or NameTool to find a project by ID or name with comprehensive details.
Get Project DomainTool to retrieve details about a specific domain attached to a Vercel project.
List Project DomainsTool to retrieve all domains attached to a Vercel project.
Get Project Environment VariableTool to retrieve the decrypted value of an environment variable from a Vercel project.
Get ProjectsTool to retrieve a list of projects from Vercel.
List Promote AliasesTool to get a list of aliases with status for the current promote operation.
Get Rolling ReleaseTool to retrieve active rolling release information for a Vercel project.
Get Rolling Release Billing StatusTool to retrieve the rolling release billing status for a Vercel project.
Get Rolling Release ConfigTool to get rolling release configuration for a Vercel project.
Get Shared Environment VariableTool to retrieve the decrypted value of a Shared Environment Variable by id.
List Shared Environment VariablesTool to list all shared environment variables for a team.
Get Team DetailsRetrieves detailed information about a specific Vercel team by its ID or slug.
Get All TeamsTool to list all teams accessible to the authenticated user with detailed information.
Get TLD InfoTool to get information about a specific top-level domain (TLD).
Get TLD PriceTool to get pricing information for a specific top-level domain (TLD).
List User EventsTool to list user events.
Get WebhookTool to retrieve details of a specific webhook by ID.
Invalidate Cache By Source ImagesTool to invalidate edge cache by source image URLs.
Invalidate Cache By TagsTool to invalidate edge cache by tags.
List Vercel AliasesTool to list aliases from Vercel API.
List Auth TokensTool to list authentication tokens.
List Deployment AliasesTool to list all aliases assigned to a specific deployment.
List Deployment ChecksTool to retrieve a list of checks for a specific deployment.
List Deployment FilesTool to list all files in a specific deployment.
List DNS RecordsTool to list existing DNS records for a domain.
Get DomainsTool to list all domains from Vercel.
Get Edge Config BackupsTool to retrieve backups for a specific Edge Config.
Get Edge Config ItemsTool to retrieve all items from a specific Edge Config.
Get Edge ConfigsTool to retrieve all Edge Configs for an account or team.
Get Edge Config TokensTool to get all tokens of an Edge Config.
Get Firewall Events by ProjectRetrieve firewall events and security actions for a specific Vercel project.
Get Integration Log DrainsRetrieves a list of Integration log drains for a team or account.
Get Project Custom EnvironmentsTool to retrieve custom environments for a Vercel project.
Get Project MembersTool to list all members of a Vercel project.
Get Supported TLDsTool to retrieve all TLDs (top-level domains) supported by Vercel for domain registration.
Get Team MembersTool to list all members of a Vercel team.
Get List of WebhooksTool to retrieve a list of all webhooks for the authenticated account or team.
Move Project DomainTool to move a domain from one Vercel project to another.
Pause Vercel ProjectTool to pause a Vercel project.
Read Firewall ConfigurationTool to read firewall configuration for a Vercel project.
Record Artifacts Cache EventsTool to record artifacts cache usage events.
Remove Domain from ProjectTool to remove a domain from a Vercel project.
Update Vercel Firewall ConfigurationTool to update firewall configuration for a Vercel project.
Request Delete User AccountTool to initiate user account deletion on Vercel.
Promote Deployment to ProductionTool to promote a deployment to production by pointing all production domains for a project to the given deployment.
Search Git RepositoriesTool to search and list Git repositories linked to a namespace by provider.
Test Drain ConfigurationTool to validate a drain delivery configuration by sending a test request.
Transfer In DomainTool to transfer a domain to Vercel from another registrar.
Unlink Shared Environment VariableTool to disconnect a shared environment variable from a Vercel project.
Unpause Vercel ProjectTool to unpause a specific project by its ID.
Update Attack Challenge ModeTool to update Attack Challenge mode for a Vercel project.
Update DNS RecordTool to update an existing DNS record.
Patch DomainTool to update or move an apex domain on Vercel.
Update Edge ConfigTool to update an Edge Config by changing its slug.
Update Edge Config ItemsTool to update items within a specific Edge Config.
Update Edge Config SchemaTool to update the JSON Schema for an Edge Config.
Update Firewall ConfigurationTool to incrementally update Vercel Firewall configuration for a project using PATCH.
Update Vercel Project (v2)Tool to update an existing Vercel project configuration.
Update Project Data CacheTool to update the data cache feature for a Vercel project.
Update Project DomainTool to update a project domain in Vercel.
Update Project Protection BypassTool to update protection bypass for automation on a Vercel project.
Update Shared Env VariableTool to update one or more shared environment variables.
Update Project Static IPsTool to configure Static IPs for a Vercel project.
Update TeamTool to update a Vercel team's configuration.
Update URL Protection BypassTool to update the protection bypass for a URL.
Upload Cache ArtifactTool to upload a cache artifact to Vercel.
Upload Deployment FileTool to upload deployment files to Vercel.
Verify Project DomainAttempts to verify a project domain by checking if DNS challenges are correctly configured.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Vercel account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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 python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Vercel via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Vercel connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async 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
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Vercel tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Vercel assistant agent with MCP tools
    agent = AssistantAgent(
        name="vercel_assistant",
        description="An AI assistant that helps with Vercel operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Vercel tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Vercel related question or task to the agent.\n")

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

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

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Vercel tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

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

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async 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 MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Vercel assistant agent with MCP tools
        agent = AssistantAgent(
            name="vercel_assistant",
            description="An AI assistant that helps with Vercel operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Vercel related question or task to the agent.\n")

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

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

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Vercel through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Vercel, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Vercel MCP Agent with another framework

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 Autogen?

Yes, you can. Autogen 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
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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.