How to Use the CodeRabbit MCP in OpenAI Agents SDK

Q: How do I configure CodeRabbit MCP tool discovery in my openai-agents-sdk setup?

Install openai-agents and pass the Vinkius HTTP endpoint to MCPServerStreamableHttp. The SDK automatically discovers tools like listusers and getmetrics without manual schema definitions. Set cacheToolsList=True to speed up agent initialization.

Q: How does openai-agents-sdk handle CodeRabbit audit log analysis?

Your agent calls getauditlogs to retrieve recent organization events as raw JSON. The SDK then streams this data directly into your agent's context window. From there, the agent can analyze compliance patterns or flag unexpected role changes.

Q: Does this server require the Enterprise plan?

Only specific tools like updateseatmode require a CodeRabbit Enterprise plan. Core tools such as listusers and getmetrics work perfectly on standard plans. Check your billing tier before letting your agent run seat-mode updates.

Control CodeRabbit seats and pull PR metrics directly from your production OpenAI Agents SDK workflows via 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 CodeRabbit MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage CodeRabbit seats inside OpenAI Agents SDK

This MCP Server exposes `assign_seats` and `unassign_seats` to let your OpenAI Agents SDK system provision access dynamically. When your onboarding agent detects a new engineer on GitHub, it automatically executes these tools to update your team's access. You don't have to write custom API wrappers for seat management anymore. The agent handles the allocation in real time, checking the current state via `get_seat_mode` before making changes.

Audit admin roles during agent handoffs

Your agent uses `promote_users` and `demote_users` to enforce strict permission boundaries. When an OpenAI Agents SDK supervisor agent hands off tasks to a sub-agent, it uses this MCP Server to check that only verified admins execute these role changes. You get full execution tracing on your OpenAI dashboard. If a sub-agent attempts an unauthorized promotion, the built-in SDK guardrails block the action before it hits CodeRabbit.

Pull pull request review metrics automatically

The `get_metrics` tool lets your OpenAI Agents SDK agent extract raw PR review performance data through the MCP. Instead of manually exporting spreadsheets, your agent queries these metrics over custom date ranges to generate engineering health reports. Combine this with `get_audit_logs` to monitor compliance across your entire development team. Your agent processes these logs to flag anomalous admin actions instantly.

Setup guide

Set up CodeRabbit 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 CodeRabbit tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and pass the Vinkius HTTP endpoint to `MCPServerStreamableHttp`. The SDK automatically discovers tools like `list_users` and `get_metrics` without manual schema definitions. Set `cacheToolsList=True` to speed up agent initialization.

Yes, you can enforce this using the SDK's native guardrails. Before the agent calls `assign_seats` or `unassign_seats`, the guardrail validates the user ID against your internal database. This prevents the agent from modifying seats for unauthorized accounts.

Your agent calls `get_audit_logs` to retrieve recent organization events as raw JSON. The SDK then streams this data directly into your agent's context window. From there, the agent can analyze compliance patterns or flag unexpected role changes.

Only specific tools like `update_seat_mode` require a CodeRabbit Enterprise plan. Core tools such as `list_users` and `get_metrics` work perfectly on standard plans. Check your billing tier before letting your agent run seat-mode updates.

Your audit logs, user IDs, and seat metrics pass through an ephemeral V8 sandbox. Vinkius does not store this data. It only acts as a secure, zero-trust bridge between your OpenAI agent and the CodeRabbit API.

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