How to Use the Linear MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK automatically close resolved Linear tickets?

Yes, your agent can use updatelinearissue to modify ticket states when a pull request merges. You can set up guardrails in Python to ensure the agent only closes tickets that meet your specific criteria.

Q: How do I manage sprint cycles in Linear with OpenAI Agents SDK?

Your agent uses listlinearcycles to find the active sprint and listlinearissues to pull the current workload. From there, it can reassign tasks or update priorities based on your team's real-time capacity.

Build production-grade Python agents that triage issues and update cycles in Linear using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear MCP to OpenAI Agents SDK

Create your Vinkius account to connect Linear to OpenAI Agents SDK 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 Linear with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Triage issues with automated agent handoffs

This MCP Server uses `create_linear_issue` and `list_linear_issues` to let your OpenAI agents sort incoming bugs without human intervention. One agent scans the triage queue, while another specialized agent writes technical updates or routes the ticket to the correct team. You get clean, structured handoffs between your specialized Python agents. By running these tools inside the OpenAI framework, you can trace every single issue update on your developer dashboard to catch errors before they hit your production tracker.

Keep sprints on track using OpenAI guardrails

The server exposes `list_linear_cycles` and `update_linear_issue` so your agent can audit active sprints and update stale tickets. Because the OpenAI framework enforces strict runtime guardrails, you can block the agent from making bulk updates that might mess up your sprint velocity metrics. Your team gets accurate cycle tracking without manual bookkeeping. The agent checks the status of every ticket, moves blocked tasks to the next cycle, and leaves clean notes for the engineers.

Add context to tickets using OpenAI tracing

This MCP tool integration uses `create_linear_comment` and `get_linear_issue` to append debugging logs directly to your issue tracker. When an agent detects a system failure, it pulls the full payload and attaches it as a structured comment. Using the SDK's built-in tracing, you can verify exactly why an agent modified a ticket. No more guessing why a bug was closed or who authorized the status change.

Setup guide

Set up Linear MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Linear tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Linear tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Linear tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Linear Agent",
            instructions="You have access to Linear tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Linear. 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 Linear 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 Linear MCP in OpenAI Agents SDK

Install the SDK using pip, then spin up the HTTP transport using `MCPServerStreamableHttp` pointed at your Vinkius MCP endpoint. Pass the server instance directly to your agent constructor, and the model will auto-discover all eleven tracking tools.

Yes, your agent can use `update_linear_issue` to modify ticket states when a pull request merges. You can set up guardrails in Python to ensure the agent only closes tickets that meet your specific criteria.

Your agent uses `list_linear_cycles` to find the active sprint and `list_linear_issues` to pull the current workload. From there, it can reassign tasks or update priorities based on your team's real-time capacity.

You can configure tool access directly in your Python agent definition by filtering the discovered tools before passing them to the constructor. This keeps your agent focused on safe actions like listing issues rather than modifying critical team settings.

This server only touches your issue titles, descriptions, comments, and cycle metadata. Vinkius runs the integration in a secure, ephemeral V8 sandbox, meaning your raw database credentials and API tokens are never exposed to the LLM or stored on disk.

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