How to integrate Raisely MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Raisely logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Raisely to AutoGen using the Composio tool router. By the end, you'll have a working Raisely agent that can list all active fundraising campaigns, show all fundraising profiles for a campaign, retrieve recent posts from our raisely site through natural language commands.

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

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

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

The Raisely MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Raisely account. It provides structured and secure access to your fundraising campaigns, so your agent can perform actions like listing campaigns, managing profiles, retrieving fundraising posts, and overseeing users or webhook subscriptions on your behalf.

  • Campaign discovery and management: Instantly fetch and list all your Raisely campaigns, making it easy to organize or review ongoing fundraising efforts.
  • Profile and supporter insights: Retrieve detailed fundraising profiles within any campaign, or list all supporter profiles to track progress and engagement.
  • Posts and communications access: Pull all posts published on the Raisely platform, allowing your agent to keep you updated or summarize campaign communications.
  • User administration: Get a comprehensive list of users on your platform or drill into user-specific fundraising profiles, streamlining supporter management.
  • Webhook and event monitoring: View all configured webhook subscriptions and available event types, helping you automate notifications and stay on top of campaign activity.

Supported Tools & Triggers

Tools
Check Profile URL AvailabilityTool to verify if a profile URL is available for a given campaign and get suggestions if unavailable.
Check User RegistrationTool to check if a user is already registered to a campaign with a specific email address.
Create CampaignTool to create a new campaign in Raisely.
Create Offline DonationTool to record an offline donation in Raisely.
Create Exercise LogTool to create a new exercise log in Raisely.
Create InteractionTool to create a new interaction in Raisely.
Create PostCreate a new post in Raisely.
Create Promo CodeTool to create a new promo code in Raisely.
Create WebhookTool to add a new webhook to your Raisely account.
Delete Exercise LogTool to delete an exercise log from Raisely.
Delete InteractionTool to delete an existing custom interaction from Raisely.
Delete Raisely PostTool to delete a post from the Raisely platform.
Delete ProfileTool to archive a profile in Raisely.
Delete Raisely WebhookTool to delete a webhook from the Raisely platform.
Retrieve Raisely API Documentation SummaryRetrieve a summary of the Raisely API documentation including metadata and sample endpoints.
Authenticate TokenAuthenticate a token to confirm it's valid and check the logged-in user.
Get Available EventsTool to retrieve a list of available Raisely webhook events.
Get CampaignTool to retrieve a specific campaign from Raisely.
Get Campaign ProfileTool to retrieve the campaign profile for a Raisely campaign.
Get campaignsTool to retrieve a paginated list of campaigns from Raisely.
List Campaign ProfilesList all fundraising profiles in a Raisely campaign.
Get Exercise LogRetrieve a specific exercise log by UUID from the Raisely platform.
Get InteractionTool to retrieve a specific interaction from Raisely by its UUID.
Get PostTool to retrieve a specific post from the Raisely fundraising platform.
Get ProfileRetrieves a specific fundraising profile from Raisely by UUID or path.
Raisely Get ProfilesRetrieves a paginated list of fundraising profiles for a Raisely campaign.
Get UserTool to retrieve a specific user from Raisely by UUID.
Get User ProfilesTool to retrieve all profiles associated with a specific user.
Get UsersRetrieve a paginated list of users from the Raisely platform.
List Campaign DonationsTool to retrieve donations from a specific campaign in Raisely.
List Campaign ProductsRetrieves all products available in a Raisely campaign.
List Campaign SubscriptionsList all subscriptions for a specific Raisely campaign.
Raisely List DonationsRetrieve donations from Raisely.
Raisely List Exercise LogsRetrieve exercise logs from Raisely.
List Interaction CategoriesTool to retrieve all interaction categories in the organisation from Raisely.
List InteractionsTool to retrieve all interactions from Raisely.
List OrdersTool to retrieve all orders in a campaign from Raisely.
List PostsTool to retrieve a list of posts you've previously created on Raisely.
List Profile DonationsRetrieves a paginated list of donations for a specific fundraising profile from Raisely.
List Profile MembersRetrieves a paginated list of all members belonging to a team profile in Raisely.
List Profile PostsList all posts created by a specific profile in Raisely.
List Promo CodesTool to retrieve all promo codes in a campaign from Raisely.
List SegmentsTool to retrieve all segments from Raisely.
Raisely List Subscriptions 2Tool to retrieve subscriptions from Raisely.
List TagsTool to retrieve the list of tags from Raisely.
List User DonationsRetrieves a paginated list of donations for a specific user from Raisely.
List User InteractionsRetrieves all interactions for a given user from Raisely.
Raisely List User SubscriptionsRetrieve subscriptions for a specific user from Raisely.
List WebhooksTool to retrieve the list of webhooks configured for a campaign.
Move DonationTool to move a donation to a different profile in Raisely.
Logout from RaiselyTool to invalidate the current user's token and log out.
Create UserCreate a new user in Raisely.
Update CampaignTool to update an existing campaign in Raisely.
Update Campaign ConfigTool to update a specific configuration attribute for a campaign in Raisely.
Update Exercise LogUpdate an existing exercise log in Raisely.
Update PostTool to update a specified post in Raisely.
Update ProfileUpdates a specific profile in Raisely.
Update UserTool to update a specified user in Raisely.
Update WebhookTool to update a specified webhook in Raisely.
Upload Campaign MediaTool to upload one or more files to a campaign's media library in Raisely.
Upsert UserTool to upsert a user record in Raisely, optionally tagging and creating an interaction.

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

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Raisely 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 Raisely 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 Raisely 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 Raisely session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["raisely"]
    )
    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 Raisely 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 Raisely assistant agent with MCP tools
    agent = AssistantAgent(
        name="raisely_assistant",
        description="An AI assistant that helps with Raisely 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 Raisely 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 Raisely 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 Raisely 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 Raisely 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 Raisely session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["raisely"]
    )
    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 Raisely assistant agent with MCP tools
        agent = AssistantAgent(
            name="raisely_assistant",
            description="An AI assistant that helps with Raisely 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 Raisely 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 Raisely 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 Raisely, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Raisely MCP Agent with another framework

FAQ

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

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

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

Yes, absolutely. You can configure which Raisely 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 Raisely 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.