How to Use the GitHub MCP in OpenAI Agents SDK

Connect your production OpenAI Agents SDK pipelines directly to GitHub repos without writing custom API integration code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitHub MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automatic issue triage with OpenAI Agents SDK

The `create_new_issue` tool exposes issue creation to your agent, letting it flag bugs and document user feedback programmatically. Your agent monitors incoming alerts, checks existing logs, and registers tickets with precise labels. You do not need to manually map payloads. By invoking `list_repository_issues`, the agent scans the active queue to prevent duplicate tickets before writing a new one. This keeps your issue board clean without manual engineering intervention.

Codebase inspection and context gathering

The `get_file_content` tool allows your agent to read source code directly from any repository branch. It pulls raw files on demand, feeding exact code blocks to the LLM for analysis or refactoring tasks. Finding the right files is fast. Your agent uses `search_repositories` to locate the target project, then runs `list_repo_branches` to pinpoint the correct branch before extracting the code.

Secure pull request audits via MCP Server

The `list_pull_requests` tool gives your agent visibility into open pull requests for automated code review pipelines. It reads through proposed changes, letting your agent run checks and flag potential issues before human review. This MCP Server runs inside a secure sandbox to protect your private code. You only manage a single Vinkius token, keeping your main GitHub credentials safe from the agent execution environment.

Setup guide

Set up GitHub 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 GitHub tools at runtime.
3

Create your Agent

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

Run the agent

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

Vinkius handles the authentication handshake on our infrastructure, so you do not store raw tokens in your agent environment. You simply pass your Vinkius endpoint URL to the `MCPServerStreamableHttp` constructor. This setup keeps your credentials isolated from the runtime.

Yes, the SDK handles concurrent tool calls natively when your agent invokes tools like `list_my_repositories` or `list_recent_notifications`. The Vinkius MCP Server manages the API rate limits to prevent your execution thread from crashing.

Your Vinkius connector requires read and write permissions depending on the tools your agent calls. If you only want to inspect code, restrict the token to read-only tools like `get_repository_details` and `list_repo_branches`. For ticketing, you must enable write access for `create_new_issue`.

This MCP connector intercepts your agent's API requests and applies queuing to prevent hitting GitHub's secondary rate limits. If your agent calls `list_my_gists` repeatedly, the platform spaces out the requests to keep your production pipeline running without throwing 403 errors.

This integration interacts with repository metadata, issue text, pull request diffs, and file contents. Every request goes through a secure V8 sandbox that destroys the runtime state immediately after execution. Your code remains private and never trains any models.

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