How to Use the Gitee MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system create issues on Gitee automatically?

Yes. The agent uses the createissue tool after discovering bugs. You can set up guardrails in the SDK to inspect the issue body and title before the agent sends the payload to Gitee.

Run secure, multi-agent workflows on Gitee with the OpenAI Agents SDK and guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gitee MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe repository setup via OpenAI Agents SDK

The `create_repo` tool lets your agent provision new Gitee repositories with strict validation guardrails before execution. You write the rules in Python, and the SDK stops unauthorized creations before they hit the Gitee API. Once the repository is live, the agent uses `list_user_repos` to verify the state and log the setup. This prevents runaway loops in your Gitee organization and keeps your resource footprint clean.

Autonomous Gitee issue triage and tracking

Your agent uses `list_repo_issues` to pull raw customer feedback directly from your active Gitee projects. It parses the text, extracts bug reports, and uses `create_issue` to file clean tracking items. The OpenAI dashboard traces every step of this triage process. You see exactly how the agent decided to format the Gitee issue, giving you full visibility into the execution path without logging into the web interface.

Multi-agent Gitee PR reviews

This MCP Server exposes `list_pull_requests` and `get_file_content` to coordinate code reviews between specialized agents. One agent pulls the code, while a secondary security agent scans the file contents for vulnerabilities. After the scan, a third agent uses `create_pull_request` to submit necessary patches. The SDK manages handoffs between these specialized agents, keeping your Gitee code review pipeline completely automated.

Setup guide

Set up Gitee 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 Gitee tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip, then initialize the server streamable HTTP class with your Vinkius endpoint. Pass this instance directly into the agent constructor under the server list parameter to auto-discover all Gitee tools.

Yes. The agent uses the `create_issue` tool after discovering bugs. You can set up guardrails in the SDK to inspect the issue body and title before the agent sends the payload to Gitee.

Set the cache tools list parameter to true to avoid redundant schema lookups. The SDK caches the tool definitions, saving your API quota for actual MCP operations like `list_repo_commits` and `get_repo`.

You control access at the authentication layer when setting up your token in Vinkius. The agent will only see repositories returned by the MCP client that match your token scopes.

Your Gitee file contents, issues, and repository metadata transit through secure, ephemeral V8 isolates. No code is stored on Vinkius servers, and the OpenAI Agents SDK communicates directly over HTTPS with your credentials.

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