How to Use the Bitbucket MCP in OpenAI Agents SDK

Q: How do I connect my Bitbucket repositories to the OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this instance in the mcpservers list when instantiating your agent to auto-discover all ten repository tools.

Q: Can I cache tools to speed up Bitbucket queries in OpenAI Agents SDK?

Yes. Set cacheToolsList=True in your configuration. This prevents your OpenAI Agents SDK from repeatedly querying the Bitbucket MCP Server for the tool schema, saving valuable latency on every run.

Q: How does the OpenAI Agents SDK handle Bitbucket pipeline failures?

Your agent calls listpipelines to fetch the status. If a pipeline fails, the agent uses listcommits to pinpoint the exact commit that broke the build, letting you write custom guardrails to block bad code.

Ship code safer by letting your OpenAI Agents SDK inspect Bitbucket PRs and run pipelines with built-in runtime guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bitbucket MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded Bitbucket PR Reviews with OpenAI Agents SDK

Your OpenAI Agents SDK uses the `get_pull_request` tool to inspect code changes and check them against your custom safety rules before any execution. This setup stops your autonomous agents from making unapproved modifications to your repositories. By combining `list_pull_requests` with OpenAI's native tracing dashboard, you monitor every step of the review. The agent flags security issues in the pull request while keeping a clean, auditable log of its decisions in your dashboard.

Workspace Discovery via Bitbucket MCP Server

The `list_workspaces` tool lets your agent map out accessible codebases and hand off tasks to specialized sub-agents. This keeps your main assistant focused on high-level decisions while worker agents dig into specific repositories. When the agent needs to inspect a branch, it calls `list_branches` to find the exact target. Because the MCP Server handles the transport, your OpenAI agents switch between repositories without losing their execution context.

Automated Pipeline Tracking and Commit Auditing

Your agent runs `list_pipelines` to check if recent commits broke the build, giving your system real-time feedback on deployment health. It maps these pipeline failures directly back to individual changes using `list_commits`. If a build fails, the agent queries `get_repository` to find the owner and logs the issue. This creates a self-healing deployment loop where the OpenAI Agents SDK identifies the breaking commit and alerts the team instantly.

Setup guide

Set up Bitbucket 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 Bitbucket tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this instance in the `mcp_servers` list when instantiating your agent to auto-discover all ten repository tools.

Yes. Set `cacheToolsList=True` in your configuration. This prevents your OpenAI Agents SDK from repeatedly querying the Bitbucket MCP Server for the tool schema, saving valuable latency on every run.

Your agent calls `list_pipelines` to fetch the status. If a pipeline fails, the agent uses `list_commits` to pinpoint the exact commit that broke the build, letting you write custom guardrails to block bad code.

You control tool access directly in your agent definition. By omitting specific tools like `list_issues` from the exposed list, you ensure your agent only reads what it needs to perform its task.

Vinkius runs the server in an ephemeral V8 Isolate sandbox, meaning your commit history and repository structures are never stored. Your credentials and code details stay strictly between your OpenAI Agents SDK and the Bitbucket MCP Server.

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