SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Productlane MCP with Autogen

Connect Autogen to Productlane MCP. Open productlane widget for user feedback, display specific docs article in widget, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Productlane logoProductlane
Api Key

Productlane is a customer support and feedback platform built on Linear. It helps companies collect, organize, and act on customer feedback for better product decisions.

39 Tools

Introduction

This guide walks you through connecting Productlane to AutoGen using the Composio tool router. By the end, you'll have a working Productlane agent that can collect feedback and insights, publish changelog entries, manage companies and contacts, and read help articles through natural language commands.

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

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

Also integrate Productlane with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic 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 Productlane
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Productlane tools
  • Run a live chat loop where you ask the agent to perform Productlane 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 Productlane MCP server, and what's possible with it?

The Productlane MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Productlane account. It provides structured and secure access to your customer feedback and support workflows, so your agent can programmatically control the Productlane widget, surface documentation, listen for widget events, and manage user interaction—all on your behalf.

  • Dynamic widget control: Let your agent open, close, enable, disable, or toggle the Productlane widget in response to customer or team actions.
  • Contextual docs surfacing: Automatically display specific Productlane documentation articles within the widget to assist users at the right moment.
  • Event-driven automation: Register or remove event listeners so your agent can react to widget events like open, close, submit, or widget load—enabling smart, real-time workflows.
  • Seamless widget experience: Programmatically manage the widget's state across your app to ensure users always get the right support touchpoint.
  • Custom interaction flows: Use the widget's event system to trigger your own logic or follow-ups based on how users interact with Productlane support.

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

Supported Tools

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

Create Changelog Entry

Tool to create a new changelog entry in Productlane.

Create Company

Tool to create a new company in Productlane.

Create Contact

Tool to create a new contact in your Productlane workspace with optional company linking.

Create Feedback

Tool to create new feedback in Productlane.

Create Insight

Tool to create a new insight/thread in Productlane workspace.

Create Thread

Tool to create a new thread in Productlane.

Create Upvote

Tool to create an upvote for a project or issue.

Delete Company

Tool to delete a company by its unique ID.

Delete Contact

Tool to delete a contact by ID.

Delete Upvote

Tool to delete an upvote by its unique ID.

Enable Productlane Widget

Return a client-side instruction to invoke Productlane.

Get Changelog

Retrieve a published Productlane changelog by workspace ID and changelog ID, optionally specifying a language.

Get Company by ID

Tool to retrieve a company by its unique ID.

Get Contact

Tool to retrieve a contact by ID or email from Productlane.

Get Help Center Article

Tool to retrieve a help center article by its ID.

Get Insight

Tool to retrieve an insight/thread by its ID.

Get Issue by ID

Tool to retrieve a specific issue by its ID from a workspace.

Get Linear Customer Options

Tool to retrieve available Linear customer statuses and tiers for your workspace.

Get Project

Tool to retrieve a project by its ID from a workspace.

Get Workspace

Tool to fetch workspace details by ID.

Invite User to Workspace

Tool to invite a new user to your Productlane workspace.

List Changelogs

Tool to list all published changelogs for a workspace by ID.

List Companies

Tool to list all companies in Productlane.

List contacts

Tool to retrieve all contacts for your workspace.

List Help Center Articles

Tool to list all help center articles for a specific workspace.

List Insights

Tool to list all threads/insights for your workspace with optional filtering.

List Productlane Issues

Tool to retrieve all issues from a Productlane workspace.

List Workspace Members

Tool to retrieve all members of your workspace with their roles and user information.

List Projects

Tool to retrieve all projects within a workspace.

Update Company

Tool to update an existing company record in Productlane by its unique identifier.

Update Contact

Tool to update an existing contact in Productlane.

Update Insight

Tool to update an existing insight (thread) by ID.

Close Productlane Widget

Generate an HTML script snippet that calls Productlane.

Disable Productlane Widget

Return a client-side instruction to invoke Productlane.

Widget off event

Generate a JavaScript snippet to remove a Productlane widget event listener for the specified event and callback.

Register Widget Event Listener

Generate a JavaScript snippet to register a Productlane widget event listener for open, close, submit, or widgetLoaded with the supplied callback.

Open Productlane Widget

Tool to generate a JavaScript snippet that opens the Productlane widget.

Open Productlane Docs Article in Widget

Generate a JavaScript snippet to open a specific docs article in the Productlane widget by document URL name or ID.

Toggle Productlane Widget

Generate a JavaScript snippet to toggle the Productlane widget between open and closed states.

FRAMEWORKS

How to build Productlane MCP Agent with another framework

Claude Code logo

Claude Code

Use Productlane MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Productlane MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Productlane MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Productlane MCP with Claude Agent SDK

Codex logo

Codex

Use Productlane MCP with Codex

OpenClaw logo

OpenClaw

Use Productlane MCP with OpenClaw

Hermes logo

Hermes

Use Productlane MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Productlane MCP with Atomic Agent

Google ADK logo

Google ADK

Use Productlane MCP with Google ADK

LangChain logo

LangChain

Use Productlane MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Productlane MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Productlane MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Productlane MCP with LlamaIndex

CrewAI logo

CrewAI

Use Productlane MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Productlane MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Productlane.It takes 30 seconds.

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

Start building