How to integrate Centralstationcrm MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Centralstationcrm Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Centralstationcrm to AutoGen using the Composio tool router. By the end, you'll have a working Centralstationcrm agent that can add new company to crm contacts, log a sales opportunity for a client, count total people in my crm, record a birthday for an existing contact through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Centralstationcrm account through Composio's Centralstationcrm 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 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 Centralstationcrm
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Centralstationcrm tools
  • Run a live chat loop where you ask the agent to perform Centralstationcrm 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 Centralstationcrm MCP server, and what's possible with it?

The Centralstationcrm MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Centralstationcrm account. It provides structured and secure access to your customer relationship data, so your agent can perform actions like managing contacts, creating deals, updating company records, and tracking key interactions on your behalf.

  • Automated contact management: Quickly add new people to your CRM, update their details, and ensure your contact database stays current without manual entry.
  • Company and organization creation: Effortlessly create new company records so you can keep your account-based selling and organization tracking up-to-date.
  • Deal tracking and creation: Instantly log new sales opportunities by creating deals linked to your contacts or companies, helping your team stay on top of the pipeline.
  • Detailed relationship enrichment: Add addresses, assistants, avatars, and contact details to people in your CRM, making every customer profile richer and more actionable.
  • Milestone and history recording: Record important life events or milestones (like birthdays or anniversaries) for each person to boost relationship management and personalized outreach.

Supported Tools & Triggers

Tools
Check ConnectionTool to verify the connection status of the centralstationcrm api key.
Count PeopleTool to retrieve the total number of people in the account.
Create CompanyTool to create a new company record.
Create DealTool to create a new deal record.
Create PersonTool to create a new person record.
Create Person AddressTool to create a new address for a specific person.
Create Person AssistantTool to create a new assistant (assi) entry for a specific person.
Create Person AvatarTool to create a new avatar for a specific person.
Create Person Contact DetailTool to create a new contact detail for a specific person.
Create Person Historic EventTool to create a new historic event for a specific person.
Delete CompanyTool to delete a company record by id.
Delete personTool to delete a person record by id.
Delete Person AddressTool to delete a person's address by its id.
Delete Person AssiTool to delete an assi entry of a person.
Delete Person AvatarTool to delete a person's avatar by its id.
Delete Person Contact DetailTool to delete a contact detail of a person.
Delete Person Historic EventTool to delete a historic event of a person by its id.
Get API User MaildropTool to retrieve the current api user's maildrop for people and companies.
Get CompanyTool to retrieve details of a specific company by id.
Get DealTool to retrieve details of a specific deal by its id.
Get DealsTool to retrieve a paginated list of all deals.
Get PersonTool to retrieve details of a specific person by id.
Get Person AddressTool to retrieve a specific address of a person by address id.
Get Person AddressesTool to retrieve all addresses for a specific person.
Get Person AssiTool to retrieve a specific assi entry of a person by id.
Get Person AssisTool to retrieve all assistant entries for a specific person.
Get Person AvatarTool to retrieve a specific avatar of a person by avatar id.
Get Person AvatarsTool to retrieve all avatars for a specific person.
Get Person Contact DetailTool to retrieve a specific contact detail by id for a person.
Get Person Custom FieldsTool to retrieve all custom fields for a specific person.
Get Person Historic EventTool to retrieve a specific historic event of a person by id.
Get Person Historic EventsTool to retrieve all historic events for a specific person.
Get PersonsTool to retrieve a paginated list of all people.
Merge PersonTool to merge another person into an existing person by id.
Search RecordsSearch records
Search PeopleTool to retrieve people matching search criteria.
Stats PeopleTool to retrieve key statistics about people.
Update CompanyTool to update an existing company by id.
Update PersonTool to update an existing person by id.
Update Person AddressTool to update a specific address of a person.
Update Person AssiTool to update an assi entry of a person.
Update Person Contact DetailTool to update a specific contact detail of a person by id.
Update Person Historic EventTool to update a historic event of a person by id.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["centralstationcrm"]
    )
    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 Centralstationcrm 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 Centralstationcrm assistant agent with MCP tools
    agent = AssistantAgent(
        name="centralstationcrm_assistant",
        description="An AI assistant that helps with Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm and AutoGen:

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 Centralstationcrm session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["centralstationcrm"]
    )
    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 Centralstationcrm assistant agent with MCP tools
        agent = AssistantAgent(
            name="centralstationcrm_assistant",
            description="An AI assistant that helps with Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm 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 Centralstationcrm, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Centralstationcrm MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Centralstationcrm MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Centralstationcrm MCP with Claude Agent SDK

Google ADK

Google ADK

Use Centralstationcrm MCP with Google ADK

LangChain

LangChain

Use Centralstationcrm MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Centralstationcrm MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Centralstationcrm MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Centralstationcrm MCP with LlamaIndex

CrewAI

CrewAI

Use Centralstationcrm MCP with CrewAI

FAQ

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

With a standalone Centralstationcrm MCP server, the agents and LLMs can only access a fixed set of Centralstationcrm tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Centralstationcrm 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 Centralstationcrm tools.

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

Yes, absolutely. You can configure which Centralstationcrm 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 Centralstationcrm 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.

Book a call↗Get started for free