How to integrate Bidsketch MCP with Autogen

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

Introduction

This guide walks you through connecting Bidsketch to AutoGen using the Composio tool router. By the end, you'll have a working Bidsketch agent that can add a new client for acme corp, list all proposals for client id 1234, delete the proposal with id 5678, remove the fee from proposal id 9012 through natural language commands.

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

The Bidsketch MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bidsketch account. It provides structured and secure access to your proposals and client data, so your agent can perform actions like creating clients, managing proposals, organizing sections, and handling fees on your behalf.

  • Client creation and management: Easily have your agent add new clients to Bidsketch or retrieve detailed client information by ID.
  • Proposal organization and cleanup: Direct your agent to list, delete, or manage proposals for specific clients, streamlining your workflow and keeping things tidy.
  • Section and fee management: Let your agent add or remove proposal sections and fees, ensuring each proposal is perfectly structured before sending.
  • Webhook and automation controls: Remove webhooks or automate repetitive admin tasks to keep your Bidsketch account running smoothly with minimal manual effort.

Supported Tools & Triggers

Tools
Create ClientTool to create a client.
Delete ClientTool to delete a client and all their proposals.
Delete FeeTool to delete a fee.
Delete ProposalTool to delete a proposal and all its content.
Delete Proposal FeeTool to delete a proposal fee.
Delete Proposal SectionTool to delete a proposal section.
Delete SectionTool to delete a section.
Delete WebhookTool to delete a webhook.
Get ClientTool to get a client by id.
Get Client ProposalsTool to list proposals for a specific client.
Get ClientsTool to retrieve all clients.
Get FeeTool to get a single fee.
Get FeesTool to list all the fees for the account.
Get ProposalTool to get a proposal by id.
Get Proposal ContentTool to get a proposal with all its content (sections and fees).
Get Proposal FeeTool to get a single fee item for a proposal.
Get Proposal FeesTool to list all fees for a proposal.
Get ProposalsTool to retrieve all proposals for the account.
Get Proposal SectionTool to fetch a single proposal section.
Get Proposal SectionsTool to get all sections for a proposal.
Get Proposal StatsTool to get proposal statistics.
Get SectionTool to fetch a section by id.
Get SectionsTool to list all sections.
Get TemplatesTool to list all proposal templates saved for the account.
Create FeeTool to create a fee.
Create Proposal FeeTool to create a proposal fee.
Create Proposal SectionTool to create a proposal section.
Create SectionTool to create a section.
Create WebhookTool to create a webhook.
Update ClientTool to update a client.
Update FeeTool to update a fee.
Update ProposalTool to update a specific proposal's details.
Update Proposal FeeTool to update a proposal fee.
Update Proposal SectionTool to update a proposal section.
Update SectionTool to update a section.

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

How to build Bidsketch MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Bidsketch MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Bidsketch MCP with Claude Agent SDK

Google ADK

Google ADK

Use Bidsketch MCP with Google ADK

LangChain

LangChain

Use Bidsketch MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Bidsketch MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Bidsketch MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Bidsketch MCP with LlamaIndex

CrewAI

CrewAI

Use Bidsketch MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Bidsketch 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 Bidsketch 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