How to Use the Forgejo (Gitea Fork) MCP in OpenAI Agents SDK

Q: How do I connect Forgejo (Gitea Fork) to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp object with your MCP URL. Pass it into the mcpservers list when you initialize your Agent class.

Q: How do I debug workflow triggers in Forgejo (Gitea Fork) with OpenAI Agents SDK?

Check the OpenAI dashboard. Every time the agent calls dispatchworkflow, the payload and the server response get logged in your agent's execution trace.

Build production-ready agents that manage self-hosted repositories 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 Forgejo (Gitea Fork) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK CI/CD Trigger

This MCP Server exposes `dispatch_workflow` to let your agent trigger manual Forgejo Actions directly. You don't want humans bottlenecking deployments. When your agent finishes writing and testing a pull request, it fires the workflow without waiting for a manual click. The OpenAI Agents SDK applies your safety constraints before executing the run. If the agent tries to spam the pipeline, the built-in guardrails catch it. You get full tracing in the OpenAI dashboard for every triggered job, showing exactly what inputs the agent passed to the API.

Dynamic Token Generation

The `create_token` tool generates new personal access tokens for specific user accounts on the fly. Hardcoding credentials in your agent system is a terrible idea. This lets your specialized agents request temporary access exactly when they need it. Handoffs between agents work better when each gets its own scoped token. One agent provisions the token, hands the context to a deployment agent, and that agent executes the deployment. You track exactly which agent did what on your self-hosted instance.

Upstream Compatibility Checks

The `get_forgejo_version` and `get_gitea_version` tools pull detailed version metadata from your self-hosted instance. API drift between forks breaks automated scripts all the time. Your agent checks these endpoints first to confirm the exact API surface available before making destructive calls. Let's face it — assuming compatibility is how you break production. The agent reads the Gitea-compatible version string and adjusts its API requests accordingly. You avoid silent failures because the agent knows exactly what environment it just connected to.

Setup guide

Set up Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` object with your MCP URL. Pass it into the `mcp_servers` list when you initialize your Agent class.

Yes. The SDK automatically reads the tool registry from the server. You just set `cacheToolsList=True` to speed up the initialization.

The server itself requires an initial authentication token to connect to your API. Once connected, the agent uses that baseline access to generate scoped tokens for other tasks.

Check the OpenAI dashboard. Every time the agent calls `dispatch_workflow`, the payload and the server response get logged in your agent's execution trace.

The server accesses personal access tokens, version strings, and workflow dispatch endpoints. The OpenAI Agents SDK processes this data entirely within your defined Python environment, meaning token secrets never leave your managed infrastructure unless you explicitly log them.

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