How to Use the Bitbucket MCP in AutoGen

Q: How do AutoGen agents share Bitbucket tool outputs?

When an agent calls getpullrequest via MCP, the tool output is posted back to the group chat. All participating agents can read the pull request details and use them in their debate.

Q: Can I limit which Bitbucket tools an AutoGen agent can access?

Yes, you can register specific tools like listcommits with individual agents. For example, you can give your QA agent access to commit history while keeping your management agent restricted.

Q: How do AutoGen agents handle failing Bitbucket pipelines?

Your agents can use listpipelines to check build statuses. If a failure is found, they debate the cause and assign a developer agent to investigate the broken commit.

Let your AutoGen agents debate and coordinate on Bitbucket git workflows with 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 Bitbucket MCP to AutoGen

Create your Vinkius account to connect Bitbucket to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven PR reviews in AutoGen MCP Server

We plug `get_pull_request` and `list_commits` into your multi-agent conversations to feed PR data directly to your team. A reviewer agent analyzes the commit messages while a QA agent inspects the changes, negotiating whether the PR is ready to merge. Instead of a single model making a biased decision, the agents challenge each other's conclusions. They must reach a consensus based on the actual commit data before recommending an action using this MCP setup.

Automated pipeline monitoring

This feature uses `list_pipelines` and `list_branches` to coordinate branch health checks. A release agent tracks active builds while a security agent flags any unauthorized branch modifications. If a pipeline fails on a protected branch, the agents discuss the root cause. They analyze the branch history and coordinate the next steps without human intervention.

Repository health audits

By executing `list_repositories`, `list_issues`, and `get_user_profile`, your agents audit workspace activity. A management agent scans for abandoned repositories and open issues, assigning them to active users based on their profiles. The agents negotiate resource allocation. They debate which issues are critical and assign tasks dynamically based on user availability and repository status.

Setup guide

Set up Bitbucket MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Bitbucket tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Bitbucket_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Bitbucket data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Bitbucket_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Bitbucket data")
    print(result.messages[-1].content)

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 AutoGen

When an agent calls `get_pull_request` via MCP, the tool output is posted back to the group chat. All participating agents can read the pull request details and use them in their debate.

Yes, you can register specific tools like `list_commits` with individual agents. For example, you can give your QA agent access to commit history while keeping your management agent restricted.

Your agents can use `list_pipelines` to check build statuses. If a failure is found, they debate the cause and assign a developer agent to investigate the broken commit.

This server supports both stdio and Streamable HTTP transports. You can configure it easily in your agent's connection parameters.

Your repository metadata and commit history are processed inside an isolated, zero-trust MCP sandbox. Vinkius ensures that no conversation data or repository details are persisted after the agent session ends.

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