# How to integrate Canny MCP with Autogen

```json
{
  "title": "How to integrate Canny MCP with Autogen",
  "toolkit": "Canny",
  "toolkit_slug": "canny",
  "framework": "AutoGen",
  "framework_slug": "autogen",
  "url": "https://composio.dev/toolkits/canny/framework/autogen",
  "markdown_url": "https://composio.dev/toolkits/canny/framework/autogen.md",
  "updated_at": "2026-05-12T10:05:00.771Z"
}
```

## Introduction

This guide walks you through connecting Canny to AutoGen using the Composio tool router. By the end, you'll have a working Canny agent that can add 'urgent' tag to all critical feedback posts, create a new post on the bugs board, change status of top-voted post to 'in progress' through natural language commands.
This guide will help you understand how to give your AutoGen agent real control over a Canny account through Composio's Canny MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Canny with

- [OpenAI Agents SDK](https://composio.dev/toolkits/canny/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/canny/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/canny/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/canny/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/canny/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/canny/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/canny/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/canny/framework/cli)
- [Google ADK](https://composio.dev/toolkits/canny/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/canny/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/canny/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/canny/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/canny/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/canny/framework/crew-ai)

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

The Canny MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Canny account. It provides structured and secure access to your feedback boards, so your agent can create new posts, manage user feedback, update post status, and keep changelogs up to date—all automatically, on your behalf.
- Automated feedback collection and posting: Enable your agent to create new posts on boards, capturing fresh user suggestions or bug reports with the right context every time.
- User and comment management: Let your agent create or update user profiles, add new comments to posts, and even delete users or comments for moderation or compliance needs.
- Status and tag updates: Have your agent update post statuses to reflect progress or changes, apply tags to categorize feedback, and create new tags as your product evolves.
- Changelog automation: Seamlessly generate and publish changelog entries to keep users informed about new features or bug fixes, with full control over timing and notifications.
- Feedback voting and prioritization: Allow your agent to create or migrate votes for posts, helping you track which ideas matter most to your users with minimal manual effort.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CANNY_ADD_POST_TAG` | Add Post Tag | Tool to add a tag to a specific post. Use when you need to categorize or group content by applying an existing tag. |
| `CANNY_CHANGE_POST_STATUS` | Change Post Status | Tool to change a post's status. Use when you need to update a post's workflow stage and optionally notify voters. |
| `CANNY_CREATE_CHANGELOG_ENTRY` | Create Changelog Entry | Tool to create and optionally publish a new changelog entry. Use when you need to add a product update record, control publish timing, and notify users. Example: "Create changelog entry titled 'Version 1.2' with details '...' and publish immediately.". |
| `CANNY_CREATE_COMMENT` | Create Comment | Tool to create a new comment on a post. Use when you have the authorID and postID and want to submit feedback or replies. |
| `CANNY_CREATE_OR_UPDATE_USER` | Create or Update User | Creates a new user or updates an existing user in Canny. If a user with the given identifier (email, userID, or id) already exists, their profile is updated; otherwise, a new user is created. IMPORTANT: At least one of 'email', 'userID', or 'id' must be provided along with 'name'. Use cases: - Sync users from your application to Canny - Update user profiles (name, avatar, custom fields) - Associate users with companies for segmentation Example: Create user with email: {"name": "Jane Doe", "email": "jane@example.com"} Example: Sync app user: {"name": "John Smith", "userID": "app_user_123", "email": "john@example.com"} |
| `CANNY_CREATE_POST` | Create Post | Tool to create a new post (feature request or feedback) on a Canny board. Use this action when you need to submit new feedback or feature requests to a board. Requires a valid boardID (from list_boards) and authorID (from create_or_update_user or list_users). |
| `CANNY_CREATE_TAG` | Create Tag | Tool to create a new tag. Use when you have the boardID and tag name and need to categorize posts. |
| `CANNY_CREATE_VOTE` | Create Vote | Tool to create a vote for a post. Use when you need to record or migrate a user's vote on a post, optionally setting priority or original creation time. Example: Create a vote for postID abc123 with voterID user_456. |
| `CANNY_DELETE_COMMENT` | Delete Comment | Tool to delete a comment. Use when moderation is required to remove a specific comment by its id. Example: "Delete the comment with ID 553c3ef8b8cdcd1501ba1238." |
| `CANNY_DELETE_POST` | Delete Post | Tool to delete a post. Use when you need to permanently remove a post by its id. Example: "Delete the post with ID 553c3ef8b8cdcd1501ba1238." |
| `CANNY_CANNY_DELETE_USER` | Delete User | Tool to delete a user and their comments and votes. Use when you need to fully remove a user’s account and all associated data (e.g., GDPR compliance). |
| `CANNY_DELETE_VOTE` | Delete Vote | Tool to delete a vote. Use when you need to remove a user's vote from a specific post by its id. Example: "Delete the vote from postID abc123 for voterID user_456." |
| `CANNY_LIST_BOARDS` | List Boards | Tool to list all boards. Use when you need to retrieve every board for your company after authentication. |
| `CANNY_LIST_CATEGORIES` | List Categories | Tool to list categories. Use when fetching categories for a specific board by its ID. |
| `CANNY_LIST_COMMENTS` | List Comments | Retrieves a paginated list of comments from Canny. Comments can be filtered by board, post, author, or company. Use this action to: - Get all comments across your Canny instance - Find comments on a specific post (using postID) - List comments from a specific board (using boardID) - See comments by a specific user (using authorID) - Track feedback from a company's users (using companyID) Returns comments ordered by creation date (newest first). Use 'limit' and 'skip' for pagination. |
| `CANNY_LIST_COMPANIES` | List Companies | Tool to list companies associated with your Canny account. Use after authentication to retrieve companies with pagination support. |
| `CANNY_LIST_OPPORTUNITIES` | List Opportunities | Tool to list opportunities linked to posts. Use when you need to fetch customer opportunities synced from CRM. |
| `CANNY_LIST_POSTS` | List Posts | Tool to list posts with various filters. Use after selecting a board or to search/filter posts. |
| `CANNY_LIST_TAGS` | List Tags | Tool to list tags. Use when fetching tags optionally filtered by board ID and handling pagination. |
| `CANNY_LIST_USERS` | List Users | List all end-users in your Canny workspace with pagination support. Use this tool to: - Fetch users from your Canny workspace - Paginate through large user lists using cursor-based pagination - Get user details including email, name, admin status, and custom fields Returns a paginated list of users. Use the returned cursor to fetch subsequent pages. |
| `CANNY_LIST_VOTES` | List Votes | Retrieve votes from Canny with optional filtering by board, post, or voter. Use this action to: - Get all votes on a specific post (filter by postID) - Get all votes by a specific user (filter by voterID) - Get all votes on posts in a board (filter by boardID) - List all votes across the account (no filters) Results are paginated - use 'limit' and 'skip' parameters to navigate through pages. Check 'hasMore' in the response to determine if more results are available. |
| `CANNY_RETRIEVE_BOARD` | Retrieve Board | Tool to retrieve details of a board by its ID. Use when you need metadata for a specific board. |
| `CANNY_RETRIEVE_TAG` | Retrieve Tag | Tool to retrieve details of a tag by its ID. Use after obtaining a valid tag ID. |
| `CANNY_RETRIEVE_USER` | Retrieve User | Tool to retrieve user details by Canny user ID, app user ID, or email. Use when you have exactly one identifier and need full user information. Example: "Retrieve user with email user@example.com" |
| `CANNY_UPDATE_POST` | Update Post | Tool to update post details. Use when you need to change a post's title, details, ETA, images, or custom fields. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Canny MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Canny. Instead of manually wiring Canny APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

You will need:
- A Composio API key
- An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
- A Canny account you can connect to Composio
- Some basic familiarity with Autogen and Python async

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

Install Composio, Autogen extensions, and dotenv.
What's happening:
- composio connects your agent to Canny via MCP
- autogen-agentchat provides the AssistantAgent class
- autogen-ext-openai provides the OpenAI model client
- autogen-ext-tools provides MCP workbench support
```bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools
```

### 3. Set up environment variables

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 Canny connections to use
```bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com
```

### 4. Import dependencies and create Tool Router session

What's happening:
- load_dotenv() reads your .env file
- Composio(api_key=...) initializes the SDK
- create(...) creates a Tool Router session that exposes Canny tools
- session.mcp.url is the MCP endpoint that Autogen will connect to
```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 Canny session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["canny"]
    )
    url = session.mcp.url
```

### 5. Configure MCP parameters for Autogen

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
```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")}
)
```

### 6. Create the model client and agent

What's happening:
- OpenAIChatCompletionClient wraps the OpenAI model for Autogen
- McpWorkbench connects the agent to the MCP tools
- AssistantAgent is configured with the Canny tools from the workbench
```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 Canny assistant agent with MCP tools
    agent = AssistantAgent(
        name="canny_assistant",
        description="An AI assistant that helps with Canny operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )
```

### 7. Run the interactive chat loop

What's happening:
- The script prompts you in a loop with You:
- Autogen passes your input to the model, which decides which Canny 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
```python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Canny 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")
```

## Complete Code

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

## How to build Canny MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/canny/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/canny/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/canny/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/canny/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/canny/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/canny/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/canny/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/canny/framework/cli)
- [Google ADK](https://composio.dev/toolkits/canny/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/canny/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/canny/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/canny/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/canny/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/canny/framework/crew-ai)

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.
- [ClickSend](https://composio.dev/toolkits/clicksend) - ClickSend is a cloud-based SMS and email marketing platform for businesses. It streamlines communication by enabling quick message delivery and contact management.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Canny MCP?

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

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

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
