How to Use the LinearB MCP in AutoGen

Q: How do I expose LinearB tools to an AutoGen assistant agent?

You use the mcpservertools adapter from autogen-extmcp to fetch the tools from the server. Then, pass the resulting tool list directly into your AssistantAgent constructor to give your agents access to your engineering metrics.

Q: How do AutoGen agents negotiate when resolving a logged LinearB incident?

A developer agent can propose logging a fix via recordnewincident, while a QA agent verifies the build status. They debate the severity and only write the record once both agents confirm the incident is mitigated.

Build multi-agent AutoGen debates to analyze delivery bottlenecks and audit LinearB metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinearB MCP to AutoGen

Create your Vinkius account to connect LinearB to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup LinearB with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on engineering bottlenecks

When delivery slows down, product managers blame developers, and developers blame QA. You can resolve this finger-pointing by setting up an AutoGen debate where a PM agent and a Dev agent analyze team performance using `list_engineering_teams` and `query_software_metrics`. The agents challenge each other's assumptions using cold, hard numbers. One agent queries cycle times while the other checks deployment frequency, forcing them to agree on the actual root cause of the bottleneck before presenting their findings to you.

Automated incident post-mortems via AutoGen agents

Writing post-mortems is a tedious task that developers hate. With this MCP Server, you can assign an incident-responder agent to gather facts by running `list_software_incidents` and matching them with recent deploys from `list_software_deployments`. A separate editor agent reviews the compiled timeline to ensure it meets your writing standards. The agents collaborate to build a complete, accurate sequence of events, saving your team hours of manual reconstruction work.

Guardrails for manual deployment and incident logging

Fat-fingering a deployment log can ruin your DORA metrics for the entire quarter. You can use a two-agent MCP setup to validate data quality before it ever reaches your dashboard. The executor agent drafts the deployment payload using `record_new_deployment` or `record_new_incident`, while a supervisor agent checks the repository ID against `list_connected_repos`. This ensures only valid, formatted data is written to your tracking system.

Setup guide

Set up LinearB MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes LinearB tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="LinearB_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LinearB data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="LinearB_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LinearB data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LinearB. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect LinearB now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about LinearB MCP in AutoGen

You use the `mcp_server_tools` adapter from `autogen-ext[mcp]` to fetch the tools from the server. Then, pass the resulting tool list directly into your `AssistantAgent` constructor to give your agents access to your engineering metrics.

Yes, the agents can share the tool suite, allowing one agent to pull data with `list_connected_repos` while another agent processes that list to query specific team metrics.

A developer agent can propose logging a fix via `record_new_incident`, while a QA agent verifies the build status. They debate the severity and only write the record once both agents confirm the incident is mitigated.

The server supports both stdio and Streamable HTTP transports. This allows you to run your multi-agent conversations locally or host them in a distributed cloud environment.

Your repository metadata and incident records are processed in a secure, ephemeral V8 isolate sandbox that does not persist any data. Vinkius acts as an MCP proxy, executing the API requests and returning the raw payloads directly to your local AutoGen environment without logging your engineering secrets.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript