How to integrate Linear MCP with Autogen

GET STARTED FOR FREE
Framework Integration Gradient
Linear Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Linear to AutoGen using the Composio tool router. By the end, you'll have a working Linear agent that can create a new bug for team mobile, add a comment to issue lin-123, list all cycles for the design team, download the latest attachment from issue lin-456 through natural language commands.

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

The Linear MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Linear account. It provides structured and secure access to your team's issues, projects, and workflows, so your agent can perform actions like creating issues, posting comments, managing attachments, organizing teams, and automating project tracking on your behalf.

  • Automated issue creation and management: Instantly create new Linear issues, update existing ones, or archive issues to keep your team’s backlog organized and up to date.
  • Commenting and collaboration: Post comments on issues, facilitate team discussions, and keep everyone in the loop without manual effort.
  • Attachment handling: Add or download attachments to and from issues, making it easy to share files or reference important documents right from Linear.
  • Team and cycle insights: Retrieve all teams, fetch cycles (sprints) by team ID, and get default issue parameters to help your agent contextualize and optimize planning activities.
  • Personalized workspace access: Identify the current user, fetch their profile information, and tailor actions or queries to individual team members for smarter automation.

Supported Tools & Triggers

Tools
Triggers
Create linear attachmentCreates a new attachment and associates it with a specific, existing linear issue.
Create a commentCreates a new comment on a specified linear issue.
Create linear issueCreates a new issue in a specified linear project and team, requiring a title and description, and allowing for optional properties like assignee, state, priority, cycle, and due date.
Get create issue default paramsFetches a linear team's default issue estimate and state, useful for pre-filling new issue forms.
Create a labelCreates a new label in linear for a specified team, used to categorize and organize issues.
Delete issueArchives an existing linear issue by its id, which is linear's standard way of deleting issues; the operation is idempotent.
Get all teamsRetrieves all teams from the linear workspace without requiring any parameters.
Download issue attachmentsDownloads a specific attachment from a linear issue; the `file name` must include the correct file extension.
Get current userGets the currently authenticated user's id, name, email, and other profile information.
Get cycles by team IDRetrieves all cycles for a specified linear team id; cycles are time-boxed work periods (like sprints) and the team id must correspond to an existing team.
Get Linear issueRetrieves an existing linear issue's comprehensive details, including title, description, attachments, and comments.
Get all cyclesRetrieves all cycles (time-boxed iterations for work) from the linear account; no filters are applied.
List Linear issuesLists non-archived linear issues; if project id is not specified, issues from all accessible projects are returned.
Get labels by teamRetrieves all labels associated with a given team id in linear; the team id must refer to an existing team.
List linear projectsRetrieves all projects from the linear account.
List Linear statesRetrieves all workflow states for a specified team in linear, representing the stages an issue progresses through in that team's workflow.
Get teams by projectRetrieves all teams, including their members, and filters each team's associated projects by the provided 'project id'.
List Linear usersLists all users in the linear workspace with their ids, names, emails, and active status.
Remove label from Linear issueRemoves a specified label from an existing linear issue using their ids; successful even if the label isn't on the issue.
Run Query or MutationWildcard action that executes any graphql query or mutation against the linear api.
Update issueUpdates an existing linear issue using its `issue id`; requires at least one other attribute for modification, and all provided entity ids (for state, assignee, labels, etc.

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

How to build Linear MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Linear MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Linear MCP with Claude Agent SDK

Google ADK

Google ADK

Use Linear MCP with Google ADK

LangChain

LangChain

Use Linear MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Linear MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Linear MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Linear MCP with LlamaIndex

CrewAI

CrewAI

Use Linear MCP with CrewAI

Claude Code

Claude Code

Use Linear MCP with Claude Code

FAQ

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

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

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

Yes, absolutely. You can configure which Linear 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 Linear 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.

Book a call↗Get started for free