How to integrate Faraday MCP with Autogen

This guide walks you through connecting Faraday to AutoGen using the Composio tool router. By the end, you'll have a working Faraday agent that can enrich salesforce leads with predictive insights, automate email categorization using faraday ai, trigger customer follow-up based on faraday scores through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Faraday account through Composio's Faraday MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Faraday logoFaraday
Api Key

Faraday lets you embed AI in workflows across your stack for smarter automation. It boosts your favorite tools with actionable intelligence and seamless integration.

117 Tools

Introduction

This guide walks you through connecting Faraday to AutoGen using the Composio tool router. By the end, you'll have a working Faraday agent that can enrich salesforce leads with predictive insights, automate email categorization using faraday ai, trigger customer follow-up based on faraday scores through natural language commands.

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

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

Also integrate Faraday with

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 Faraday
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Faraday tools
  • Run a live chat loop where you ask the agent to perform Faraday 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 Faraday MCP server, and what's possible with it?

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

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Faraday account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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 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 Faraday via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 Faraday connections to use
5

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 Faraday session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["faraday"]
    )
    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 Faraday tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Faraday assistant agent with MCP tools
    agent = AssistantAgent(
        name="faraday_assistant",
        description="An AI assistant that helps with Faraday 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 Faraday tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Faraday 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 Faraday 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 Faraday 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 Faraday session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["faraday"]
    )
    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 Faraday assistant agent with MCP tools
        agent = AssistantAgent(
            name="faraday_assistant",
            description="An AI assistant that helps with Faraday 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 Faraday 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 Faraday 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 Faraday, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Archive Cohort

Tool to archive a cohort in Faraday.

Archive Connection

Tool to archive a connection in Faraday.

Archive Dataset

Tool to archive a dataset in Faraday.

Archive Outcome

Tool to archive an outcome in Faraday.

Archive Persona Set

Tool to archive a persona set in Faraday.

Archive Place

Tool to archive a place in Faraday.

Archive Scope

Tool to archive a scope in Faraday.

Archive Stream

Tool to archive a stream in Faraday.

Archive Target

Tool to archive a target in Faraday.

Archive Trait

Tool to archive a trait in Faraday.

Create Account

Tool to create a new Faraday account with specified name and branding.

Create Cohorts

Tool to create a new cohort in Faraday.

Create Dataset

Tool to create a new dataset in Faraday.

Create Outcome

Tool to create a new outcome.

Create Persona Set

Tool to create a new persona set.

Create Place

Tool to create a new place in Faraday.

Create Scope

Tool to create a new scope in Faraday.

Create Stream

Tool to create a new stream or find an existing stream by name.

Create Target Preview

Tool to start a preview delivery for a target.

Create Target

Tool to create a target in Faraday.

Create Trait

Tool to create a new trait in Faraday.

Create Webhook Endpoint

Tool to create a new webhook endpoint.

Delete Account

Tool to delete an account by its UUID.

Delete All Orphaned Traits

Tool to delete all orphaned traits from Faraday.

Delete Cohort

Tool to permanently delete a cohort from Faraday.

Delete Connection

Tool to delete a Faraday connection by its UUID.

Delete Dataset

Tool to delete a dataset from Faraday.

Delete Outcome

Tool to delete an outcome by its UUID.

Delete Persona Set

Tool to delete a persona set.

Delete Place

Tool to delete a place by its UUID.

Delete Scope

Tool to delete a scope by its UUID.

Delete Stream

Tool to delete a stream by its UUID or name.

Delete Target

Tool to delete a target by its UUID.

Delete Upload

Permanently deletes a file from a Faraday dataset directory.

Delete Webhook Endpoint

Tool to delete a webhook endpoint by its UUID.

Force Update Cohort

Tool to trigger a rerun for a cohort.

Force Update Connection

Tool to trigger a rerun for a Faraday connection.

Force Update Dataset

Tool to trigger a rerun for a dataset.

Force Update Outcome

Tool to trigger a rerun for an outcome resource.

Force Update Persona Set

Tool to trigger a rerun for a persona set resource.

Force Update Place

Tool to trigger a rerun for a place.

Force Update Scope

Tool to trigger a rerun for a scope resource.

Force Update Stream

Tool to trigger a rerun for a stream.

Force Update Target

Tool to trigger a rerun for a target.

Force Update Trait

Tool to trigger a rerun for a trait.

Get Account

Tool to retrieve detailed information about a Faraday account by its UUID.

List Accounts

Tool to list all Faraday accounts accessible by the current user.

Get Accounts Billing

Tool to get billing information about your account.

Get Cohort

Tool to retrieve a specific cohort by ID.

Get Cohort Membership Analysis

Tool to get cohort membership counts over time for a specific cohort.

List Cohorts

Tool to list all cohorts in your Faraday account.

Get Connection Datasets

Tool to retrieve all datasets that use a specific connection.

Get Connection Targets

Tool to retrieve all targets that use a specific connection.

Get Current Account

Tool to retrieve the current account information.

Get Current Account Billing

Tool to retrieve billing information about the current account.

Get Dataset

Tool to retrieve a dataset by its UUID.

Get Dataset Ingress Logs

Tool to retrieve dataset ingress metrics over time.

List Feature Stores

Tool to list all feature stores.

Get Dependency Graph

Tool to retrieve the complete dependency graph for all resources on an account.

Get Market Opportunity Analyses

Tool to retrieve all market opportunity analyses from Faraday.

Get Outcome

Tool to retrieve an outcome by its ID.

List Outcomes

Tool to list all outcomes for the account.

Get Persona Set

Tool to retrieve a persona set by its UUID.

Get Persona Set Analysis Flow

Tool to retrieve the flow of persona sets over time, showing how individuals move between different personas.

List Persona Sets

Tool to list all persona sets.

Get Persona Set Analysis Dimensions

Tool to get various trait breakdown information about a persona set.

Get Place

Tool to retrieve a specific place by its UUID.

List Places

Tool to list all places in Faraday.

List Recommenders

Tool to list all recommenders.

Get Scope

Tool to retrieve detailed information about a Faraday scope by its UUID.

Get Scope Analysis

Tool to get analysis for a scope including outcomes and recommenders with probability distributions.

Get Scope Datasets

Tool to retrieve all datasets associated with a Faraday scope.

Get Scope Efficacy

Tool to retrieve efficacy metrics for a scope.

Get Scope Payload Cohorts

Tool to get payload cohorts for a specific scope.

Get Scope Payload Outcomes

Tool to retrieve payload outcomes for a specific scope.

Get Scope Payload Persona Sets

Tool to get payload persona sets for a specific scope.

Get Scope Payload Recommenders

Tool to retrieve payload recommenders for a specific scope.

Get Scope Population Exclusion Cohorts

Tool to get population exclusion cohorts for a scope.

Get Scope Population Cohorts

Tool to get population cohorts for a specific scope.

Get Scope Targets

Tool to get all targets for a specific scope.

Get Stream

Tool to retrieve a stream by its UUID or name.

List Streams

Tool to list all streams in your Faraday account.

Get Streams Analysis

Tool to get the count of stream events emitted over a time period.

Get Target

Tool to retrieve a specific target by its UUID from Faraday.

Get Target Analysis

Tool to retrieve a target's analysis including geographic distributions and trait breakdowns.

Get Trait

Tool to retrieve a specific trait by ID.

Get Trait Analysis Dimensions

Tool to retrieve the percentage of the US population that falls into each category of a trait.

Get Traits CSV

Tool to retrieve all user-defined and Faraday-provided traits in CSV format.

Get Upload

Tool to download a previously uploaded file from a Faraday dataset directory.

List Uploaded Files

Tool to retrieve the list of previously uploaded files in Faraday.

Get Usages

Tool to retrieve usage statistics for your Faraday account.

Get Webhook Endpoint

Tool to retrieve a webhook endpoint by its UUID.

List Webhook Endpoints

Tool to list all webhook endpoints configured for the account.

List Attributes

Tool to list all attributes in the feature store.

List Connections

Tool to list all connections configured in Faraday.

List Scopes

Tool to list all scopes.

List Targets

Tool to list all targets in your Faraday account.

Unarchive Cohort

Tool to unarchive a previously archived cohort.

Unarchive Dataset

Tool to unarchive a dataset in Faraday.

Unarchive Outcome

Tool to unarchive an outcome in Faraday.

Unarchive Persona Set

Tool to unarchive a previously archived persona set.

Unarchive Place

Tool to unarchive a previously archived place.

Unarchive Scope

Tool to unarchive a previously archived scope.

Unarchive Stream

Tool to unarchive a stream in Faraday.

Unarchive Trait

Tool to unarchive a trait.

Update Account

Tool to update an account's name or branding settings.

Update Cohort

Tool to update a cohort's configuration using JSON Merge Patch semantics.

Update Connection

Tool to update a Faraday connection's name or options.

Update Dataset

Tool to update a dataset configuration using JSON Merge Patch semantics.

Update Outcome

Tool to update an outcome's configuration using JSON Merge Patch semantics.

Update Persona Set

Tool to edit a persona set's configuration using JSON Merge Patch.

Update Place

Tool to update a place's name, addresses, or geojson geometry.

Update Scope

Tool to update a Faraday scope's configuration using JSON Merge Patch semantics.

Update Stream

Tool to update a stream's properties using JSON Merge Patch semantics.

Update Target

Tool to update a target's configuration in Faraday.

Update Trait

Tool to update a trait's properties using JSON Merge Patch semantics.

Update Webhook Endpoint

Tool to update a webhook endpoint's configuration.

FAQ

Frequently asked questions

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

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 Faraday tools.

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

Start with Faraday.It takes 30 seconds.

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

Start building