How to integrate Clientary MCP with Autogen

GET STARTED FOR FREE
Framework Integration Gradient
Clientary Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Clientary to AutoGen using the Composio tool router. By the end, you'll have a working Clientary agent that can create new invoice for a client, list all active projects this month, send payment reminder to overdue clients through natural language commands.

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

The Clientary MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Clientary account. It provides structured and secure access so your agent can perform Clientary operations on your behalf.

Supported Tools & Triggers

Tools
Create ClientTool to create a new client record in Clientary.
Create ContactTool to create a new contact within a specified client.
Create ExpenseTool to create a new expense record in Clientary to track expenditures within your account.
Create LeadTool to create a new lead record in Clientary.
Create ProjectTool to create a new project in Clientary with name and rate.
Create TaskTool to create a new task in Clientary.
Delete ClientTool to remove a client and all associated projects, invoices, estimates, and contacts.
Delete LeadTool to permanently delete a lead and all associated Estimates and Contacts.
Delete PaymentTool to remove an existing payment from an invoice.
Delete Payment ProfileTool to remove a specific payment profile from a client's account.
Delete Recurring ScheduleTool to remove a recurring schedule by its identifier.
Get ClientTool to fetch details for a specific client using its ID.
Get ContactTool to retrieve a single contact by its ID.
Get EstimateTool to retrieve details for a single estimate by ID.
Get ExpenseTool to retrieve details for a single expense record in Clientary.
Get Hour EntryTool to obtain details about a specific time entry in Clientary.
Get InvoiceTool to retrieve detailed information for a specific invoice by ID.
Get LeadTool to retrieve a single lead by its ID.
Get ProjectTool to retrieve a single project by its identifier.
Get StaffTool to retrieve a single staff member by their ID.
Get TaskTool to retrieve a specific task by its ID.
List Client ContactsTool to retrieve all contacts for a specific client with pagination support.
List Client ExpensesTool to retrieve all expenses for a specific client within an optional date range.
List Client InvoicesTool to retrieve all invoices for a specific client with pagination support (30 results per page).
List Client ProjectsTool to retrieve all projects associated with a specific client with pagination support (10 results per page).
List ClientsTool to retrieve all clients with pagination support (10 results per page).
List ExpensesTool to retrieve expenses by date range (defaults to current fiscal year).
List LeadsTool to retrieve all leads with pagination support.
List PaymentsTool to retrieve all payments with pagination support (30 results per page).
List Project EstimatesTool to retrieve estimates scoped to a particular project with pagination support (30 results per page).
List Project ExpensesTool to retrieve all expenses for a specific project within an optional date range.
List Project HoursTool to retrieve all time tracking entries logged against a specific project.
List Project InvoicesTool to retrieve all invoices linked to a specific project with pagination support (30 results per page).
List ProjectsTool to retrieve all projects with pagination support (10 results per page).
List StaffTool to retrieve all staff members for an account.
List TasksTool to retrieve all tasks with pagination support (50 results per page).
Send Invoice MessageTool to send an invoice message to recipients via email.
Update ClientTool to update an existing client record in Clientary with partial or complete field modifications.
Update ExpenseTool to update an existing expense record in Clientary with partial or complete field modifications.
Update Hour EntryTool to modify an existing time entry in Clientary with partial or complete field updates.
Update ProjectTool to update an existing project in Clientary with partial or complete field modifications.
Update TaskTool to update an existing task in Clientary with partial or complete field modifications.

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

How to build Clientary MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Clientary MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Clientary MCP with Claude Agent SDK

Google ADK

Google ADK

Use Clientary MCP with Google ADK

LangChain

LangChain

Use Clientary MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Clientary MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Clientary MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Clientary MCP with LlamaIndex

CrewAI

CrewAI

Use Clientary MCP with CrewAI

Claude Code

Claude Code

Use Clientary MCP with Claude Code

Codex

Codex

Use Clientary MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Clientary 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 Clientary 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