How to Use the Bitbucket MCP in LangChain

Q: How does LangSmith trace Bitbucket tool calls within LangChain?

LangSmith traces every single call to listpipelines or listcommits in real time. You can inspect the exact payload your LangChain agent sent and see how many tokens the response consumed.

Run multi-step Git workflows directly inside your LangChain reasoning loops 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 LangChain

Create your Vinkius account to connect Bitbucket to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Bitbucket pipeline runs with LangChain

We use `list_pipelines` and `list_commits` to feed execution data directly into your active LangChain runs. Your agent calls these tools to inspect why a build failed, matches the failure to a specific commit hash, and pipes that output to the next node in your graph. Every tool execution gets logged in LangSmith. You see the exact inputs passed to `list_pipelines` in this MCP setup, making it easy to debug flaky tests or token overhead.

Multi-step pull request auditing

This integration uses `get_pull_request` and `list_branches` to run recursive code review chains. Your agent fetches the active PR details, identifies the source branch, and pulls the branch structure to analyze changes before approval. Because it runs inside a LangChain ReAct agent using the MCP standard, the output of one step determines the next. If the PR branch is out of date, the agent halts the chain and alerts you instead of trying to merge broken code.

Workspace inventory mapping

By calling `list_workspaces`, `list_repositories`, and `list_issues`, your agent builds a real-time index of your active projects. It queries your workspaces, lists the repositories inside them, and scans for open issues to map out your team's current workload. You can feed this structured data directly into LangChain vector stores or databases. It gives your agent a clear, up-to-date map of your development assets without manual API calls.

Setup guide

Set up Bitbucket MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Bitbucket tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bitbucket-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Bitbucket transactions"
    })
    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 LangChain

You don't have to handle raw tokens in your LangChain code. Vinkius manages the authentication layer, giving your agent a single secure endpoint to call these tools.

The tools in this MCP Server are read-only, focusing on operations like `list_branches` and `get_pull_request`. Your agent can inspect and analyze your code but cannot modify or delete your repositories.

LangSmith traces every single call to `list_pipelines` or `list_commits` in real time. You can inspect the exact payload your LangChain agent sent and see how many tokens the response consumed.

Yes, that is the core benefit of this setup. You can feed the output of `list_issues` directly into a database chain or a Slack messaging tool within the same LangChain execution.

Vinkius runs this MCP Server in an isolated, ephemeral sandbox. Your repository metadata and pipeline logs are only processed to answer the agent's immediate request and are never stored or used to train models.

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