How to integrate Seam MCP with CrewAI

This guide walks you through connecting Seam to CrewAI using the Composio tool router. By the end, you'll have a working Seam agent that can list your devices and spaces, create access grants, update access grants, and review action attempts through natural language commands. This guide will help you understand how to give your CrewAI agent real control over a Seam account through Composio's Seam MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Seam logoSeam
Api Key

Seam is a connected device API for smart locks, access systems, thermostats, sensors, and other workspace devices. It gives developers one clean interface to manage building access and device state across many hardware brands.

10 Tools

Introduction

This guide walks you through connecting Seam to CrewAI using the Composio tool router. By the end, you'll have a working Seam agent that can list your devices and spaces, create access grants, update access grants, and review action attempts through natural language commands.

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

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

Also integrate Seam with

TL;DR

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

The Seam MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Seam account. It provides structured and secure access to your connected devices, spaces, accounts, and access grants, so your agent can find devices, review connected accounts, create and update access grants, revoke access, and monitor operation results on your behalf.

  • Device and space discovery: Have your agent find connected devices and grantable spaces by details such as name, type, manufacturer, customer, or workspace metadata.
  • Access grant creation: Let the agent grant new or existing users access to selected spaces, devices, or entrances using PINs, cards, mobile keys, or cloud keys.
  • Access updates and revocation: Direct your agent to change an access grant's name or validity period, add more access methods, or permanently revoke access.
  • Access and account review: Instruct your agent to review access grants and search the provider accounts connected to your workspace.
  • Operation monitoring: Have your agent check the status, errors, and results of device operations so you can see whether requested actions completed successfully.

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

Step by step08 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Seam connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python
2

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.
3

Install dependencies

bash
pip install composio crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to Seam via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env
4

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
5

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
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 Seam MCP URL
6

Create a Composio Tool Router session for Seam

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["seam"])

url = session.mcp.url
What's happening:
  • You create a Seam only session through Composio
  • Composio returns an MCP HTTP URL that exposes Seam tools
7

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.
8

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[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:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["seam"],
)
url = session.mcp.url

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

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

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

Conclusion

You now have a CrewAI agent connected to Seam through Composio's Tool Router. The agent can perform Seam 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
TOOLS

Supported Tools

Every Seam action and event your agent gets out of the box.

Add Access Methods to Grant

Request additional PIN, card, mobile-key, or cloud-key methods for an existing access grant.

Create Access Grant

Grant an existing or new user identity access to spaces, devices, or access-control entrances, requesting PIN, card, mobile-key, or cloud-key methods.

Delete Access Grant

Permanently revoke and delete an access grant by UUID, removing the access it manages.

Get Access Grant

Get one access grant by its Seam UUID or unique workspace key.

List Access Grants

List access grants in the workspace, optionally filtered by space, device, entrance, user identity, reservation, customer, key, or IDs; returns one cursor-controlled page.

List Action Attempts

Inspect asynchronous Seam operation status, errors, and results in bulk by action-attempt IDs or by device, returning one cursor-controlled page.

List Connected Accounts

List and search provider accounts connected to the workspace, optionally filtering by space, customer, user, or metadata; returns one cursor-controlled page.

List Devices

List and search devices in the workspace, optionally filtering by account, space, IDs, type, manufacturer, customer, creation time, or metadata; returns one cursor-controlled page.

List Spaces

List and search spaces in the workspace by name, key, or customer, returning one cursor-controlled page of grantable locations.

Update Access Grant

Update an access grant's name or validity window by UUID or unique workspace key.

FAQ

Frequently asked questions

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

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 Seam tools.

Yes, absolutely. You can configure which Seam 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.

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 Seam data and credentials are handled as safely as possible.

Start with Seam.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Seam tool your agent needs.Free to start.

Start building