How to integrate Instantly MCP with Autogen

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

Introduction

This guide walks you through connecting Instantly to AutoGen using the Composio tool router. By the end, you'll have a working Instantly agent that can create a new cold email campaign, add a new lead to my campaign, check unread emails in my inbox, run an inbox placement test for gmail through natural language commands.

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

The Instantly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Instantly account. It provides structured and secure access to your campaigns, leads, and outreach tools, so your agent can perform actions like launching new campaigns, managing leads, tracking inbox statistics, and handling API credentials on your behalf.

  • Automated campaign creation and management: Ask your agent to launch new cold email campaigns or update existing ones, streamlining your outreach workflow without manual setup.
  • Lead and lead list management: Let your agent add new leads, organize them into lists, or enrich them with AI-driven insights to maximize your campaign effectiveness.
  • Email verification and deliverability tracking: Direct your agent to check the verification status of email addresses or run inbox placement tests to monitor and improve deliverability across providers.
  • Inbox activity monitoring: Fetch unread email counts or campaign engagement metrics, helping you stay on top of your outreach performance in real time.
  • API key and webhook automation: Have your agent create or delete API keys for secure integrations, or set up webhooks to receive instant notifications about important Instantly events.

Supported Tools & Triggers

Tools
Check Email Verification StatusTool to check status of an email verification job.
Count Unread EmailsTool to retrieve the count of unread emails.
Create AI EnrichmentTool to create an AI enrichment job for a campaign or lead list.
Create API KeyTool to create a new API key.
Create CampaignTool to create a new campaign.
Create Inbox Placement TestTool to create an inbox placement test.
Create LeadTool to create a new lead.
Create Lead ListTool to create a new lead list.
Create WebhookTool to create a new webhook endpoint.
Delete API KeyTool to delete an API key.
Delete CampaignTool to delete a campaign.
Delete LeadTool to delete a lead by its ID.
Delete Lead ListTool to delete a lead list by ID.
Delete WebhookTool to delete a webhook.
Disable Account WarmupTool to disable the warm-up process for email accounts.
Enable Account WarmupTool to enable the warm-up process for email accounts.
Get CampaignTool to retrieve campaign details.
Get Campaign AnalyticsTool to retrieve analytics for campaigns.
Get Daily Campaign AnalyticsTool to retrieve daily analytics for a campaign.
Get Email Service Provider OptionsTool to retrieve email service provider options for inbox placement tests.
Get Inbox Placement TestTool to retrieve inbox placement test results.
Get LeadTool to retrieve details of a specific lead by its ID.
Get Lead ListTool to retrieve details of a specific lead list by its ID.
Get Lead List Verification StatsTool to retrieve verification statistics for a lead list.
Get WebhookTool to retrieve details of a specific webhook subscription.
Get Webhook EventTool to retrieve details of a specific webhook event.
List Email AccountsTool to list all email accounts for the authenticated user.
List API KeysTool to list all API keys.
List CampaignsTool to list all campaigns.
List Custom TagsTool to list custom tags.
List DFY Email Account OrdersTool to list DFY email account orders.
List EmailsTool to list emails.
List Inbox Placement Blacklist & SpamAssassin ReportsTool to list inbox placement blacklist & SpamAssassin reports.
List Inbox Placement TestsTool to list inbox placement tests.
List Lead ListsTool to list all lead lists.
List LeadsTool to list leads.
List Email ThreadsTool to list email threads.
List Webhook EventsTool to list webhook events.
List WebhooksTool to list configured webhooks.
Mark Thread As ReadTool to mark all emails in a specific thread as read.
Merge LeadsTool to merge multiple leads into a single lead.
Search Campaigns by Lead EmailTool to search campaigns by a lead's email address.
Update CampaignTool to update details of a campaign.
Update LeadTool to update a lead's details.
Update Lead Interest StatusTool to update a lead's interest status.
Update Lead ListTool to update details of a specific lead list by its ID.
Verify EmailTool to initiate email verification.

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

How to build Instantly MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Instantly MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Instantly MCP with Claude Agent SDK

Google ADK

Google ADK

Use Instantly MCP with Google ADK

LangChain

LangChain

Use Instantly MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Instantly MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Instantly MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Instantly MCP with LlamaIndex

CrewAI

CrewAI

Use Instantly MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Instantly 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 Instantly data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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