How to Use the GitHub MCP in OpenAI Agents SDK

Q: How do I initialize the GitHub MCP Server within my openai-agents-sdk project?

Install the package and configure the MCPServerStreamableHttp client with your Vinkius endpoint. Pass the server instance directly to your agent constructor using the mcpservers list to start calling tools like listuserrepositories instantly.

Q: Can my openai-agents-sdk agent query organization repos?

Yes, your agent can call listorgrepositories to find any repository inside your GitHub organization. Ensure your Vinkius token has the correct organizational permissions configured.

Run production-grade OpenAI Agents SDK workflows that manage repositories and track issues directly through the GitHub MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect GitHub MCP to OpenAI Agents SDK

Create your Vinkius account to connect GitHub to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup GitHub with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate GitHub write actions with built-in guardrails

The `create_new_issue` tool lets your agent open issues directly in your repositories, but the real power comes when you run it through the OpenAI Agents SDK. You can set up strict validation rules that block your agent from creating duplicate or malformed issues before any API call goes out. If the agent encounters a complex codebase error, it can fetch file contents using `get_file_contents` and hand the task off to a specialized debugging agent. This keeps your production system safe from runaway loops and bad commits while keeping your team in the loop.

Run secure code searches using the OpenAI dashboard

When your agent executes `search_github_code` to find specific patterns, you can trace the entire execution flow inside your OpenAI developer dashboard. This gives you exact visibility into what code snippets your agent reads and how it processes that data. You do not have to guess what your agent is doing in your codebase. Every call to `get_repository_details` or `list_org_repositories` is logged in real-time, letting you verify that the agent stays within its defined organizational boundaries.

Track pull requests via the GitHub MCP Server

The `list_pull_requests` tool exposes all active pull requests directly to your OpenAI Agents SDK pipeline. Instead of a single agent trying to handle review and merge logic, you can split these tasks between specialized agents that communicate natively. One agent can look at the pull request list, while another runs `verify_api_connection` to ensure your credentials are valid before requesting more data. This modular architecture keeps your automated code review pipelines running fast and clean.

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

Install the package and configure the `MCPServerStreamableHttp` client with your Vinkius endpoint. Pass the server instance directly to your agent constructor using the `mcp_servers` list to start calling tools like `list_user_repositories` instantly.

Yes, you can configure your OpenAI Agents SDK setup to only expose read-only tools like `get_file_contents` or `list_repo_issues`. This prevents the agent from executing write tools like `create_new_issue` in your production environments.

The SDK manages token usage and pacing, but when your agent runs `search_github_code` repeatedly, it respects standard GitHub API rate limits. You can monitor these limits and track execution times directly in your OpenAI tracing dashboard.

Yes, your agent can call `list_org_repositories` to find any repository inside your GitHub organization. Ensure your Vinkius token has the correct organizational permissions configured.

Your GitHub API tokens and repository metadata are never stored or logged on Vinkius servers. All traffic between your openai-agents-sdk agent and the GitHub API runs through an ephemeral, isolated MCP sandbox that immediately destroys session data upon completion.

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