How to Use the LinearB MCP in OpenAI Agents SDK

Connect OpenAI Agents SDK to your delivery pipeline to track deployments and incidents using this MCP Server.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate incident logging with OpenAI Agents SDK

The `record_new_incident` tool lets your agent log outages directly to your dashboard when a production check fails. This tool pairs with `list_software_incidents` so your agent can audit past failures before triggering duplicate alerts. Using this MCP Server with the OpenAI Agents SDK ensures your autonomous agents can monitor system health without manual intervention. You get full visibility of every agent-initiated incident report right inside your OpenAI tracing dashboard.

Audit team metrics using this MCP Server

The `query_software_metrics` tool retrieves cycle time and DORA metrics for any team returned by `list_engineering_teams`. Your agent handles the complex JSON payloads, parsing raw performance numbers into clean summaries for your leadership updates. Running this toolset through the OpenAI Agents SDK means you can set strict guardrails on who can query sensitive engineering metrics. The SDK validates the agent's parameters before executing the request, preventing unauthorized data dumps.

Track active deployments automatically

The `record_new_deployment` tool registers code changes in real-time by linking specific git refs to repositories found via `list_connected_repos`. Your agent uses this to map code shipping events directly to your delivery dashboard. When you register this tool in your OpenAI Agents SDK configuration, your deployment agent can pass off tasks to an incident-monitoring agent if a rollout triggers a regression. The SDK handles this multi-agent handoff under the hood while maintaining a single session.

Setup guide

Set up LinearB 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 LinearB tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LinearB 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="LinearB Agent",
            instructions="You have access to LinearB 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 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 OpenAI Agents SDK

First, install the package using pip. Next, initialize your server stream using the streamable HTTP parameters. Pass the server instance inside your agent's server list configuration, making sure to cache the tools list to optimize performance.

Yes, your agent pulls active team structures using the team listing tool and passes them to the metrics query tool. The SDK tracing dashboard logs every single query so you can audit which team data was fetched.

If registering a deployment fails due to a missing git ref, the SDK guardrails catch the error before it breaks your pipeline. Your agent then queries your connected repositories to find the correct ID and retry the write operation.

Yes, you can configure tool exposure directly inside your agent initialization code. This allows you to build a read-only agent that only runs list operations while blocking write tools like incident logging.

Your repository metadata and incident records are processed inside an ephemeral, zero-trust sandbox. The SDK communicates over encrypted HTTP channels, preventing any persistent storage of your telemetry outside your pipeline.

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