How to integrate Bitbucket MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Bitbucket Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Bitbucket to CrewAI using the Composio tool router. By the end, you'll have a working Bitbucket agent that can create a new branch off main, open a pull request for my feature, comment on the latest open issue, fetch readme file from repository through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Bitbucket account through Composio's Bitbucket MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Bitbucket connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Bitbucket
  • Build a conversational loop where your agent can execute Bitbucket operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Bitbucket MCP server, and what's possible with it?

The Bitbucket MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bitbucket account. It provides structured and secure access to your repositories, issues, and pull requests, so your agent can create branches, manage issues, review code, and handle repository operations for you.

  • Branch and repository management: Let your agent create new branches for feature work or initialize fresh repositories within your Bitbucket workspace—no manual setup required.
  • Automated issue tracking: Have your agent create, comment on, or delete issues to streamline team collaboration and bug tracking directly from your workflows.
  • Pull request automation: Empower your agent to open new pull requests for code review, ensuring changes are properly tracked and integrated.
  • File and snippet operations: Ask your agent to fetch specific files from any branch or commit, or to post comments on code snippets for contextual discussions.
  • User profile and workspace insights: Retrieve your Bitbucket user profile details on demand, making it easy to personalize and audit agent-driven actions.

Supported Tools & Triggers

Tools
Create a branchCreates a new branch in a bitbucket repository from a target commit hash; the branch name must be unique, adhere to bitbucket's naming conventions, and not include the 'refs/heads/' prefix.
Create an issueCreates a new issue in a bitbucket repository, setting the authenticated user as reporter; ensures assignee (if provided) has repository access, and that any specified milestone, version, or component ids exist.
Create an issue commentAdds a new comment with markdown support to an existing bitbucket issue.
Create a pull requestCreates a new pull request in a specified bitbucket repository, ensuring the source branch exists and is distinct from the (optional) destination branch.
Create repositoryCreates a new bitbucket 'git' repository in a specified workspace, defaulting to the workspace's oldest project if `project key` is not provided.
Create snippet commentPosts a new top-level comment or a threaded reply to an existing comment on a specified bitbucket snippet.
Delete issuePermanently deletes a specific issue, identified by its `issue id`, from the repository specified by `repo slug` within the given `workspace`.
Delete repositoryPermanently deletes a specified bitbucket repository; this action is irreversible and does not affect forks.
Get current userRetrieves the profile information (uuid, display name, links, creation date) for the currently authenticated bitbucket user.
Get file from repositoryRetrieves a specific file's content from a bitbucket repository at a given commit (hash, branch, or tag), failing if the file path is invalid for that commit.
Get Pull RequestGet a single pull request by id with complete details.
Get snippetRetrieves a specific bitbucket snippet by its encoded id from an existing workspace, returning its metadata and file structure.
List pull requestsLists pull requests in a specified, accessible bitbucket repository, optionally filtering by state (open, merged, declined).
List repositories in workspaceLists repositories in a specified bitbucket workspace, accessible to the authenticated user, with options to filter by role or query string, and sort results.
List workspace membersLists all members of a specified bitbucket workspace; the workspace must exist.
List workspacesLists bitbucket workspaces accessible to the authenticated user, optionally filtered and sorted.
Update an issueUpdates an existing issue in a bitbucket repository by modifying specified attributes; requires `workspace`, `repo slug`, `issue id`, and at least one attribute to update.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Bitbucket connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Bitbucket via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Bitbucket MCP URL

Create a Composio Tool Router session for Bitbucket

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["bitbucket"],
)
url = session.mcp.url
What's happening:
  • You create a Bitbucket only session through Composio
  • Composio returns an MCP HTTP URL that exposes Bitbucket tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Bitbucket Assistant",
    goal="Help users interact with Bitbucket through natural language commands",
    backstory=(
        "You are an expert assistant with access to Bitbucket tools. "
        "You can perform various Bitbucket operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Bitbucket MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Bitbucket operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Bitbucket related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_bitbucket_agent.py

Complete Code

Here's the complete code to get you started with Bitbucket and CrewAI:

python
# file: crewai_bitbucket_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Bitbucket session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bitbucket"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Bitbucket assistant agent
    toolkit_agent = Agent(
        role="Bitbucket Assistant",
        goal="Help users interact with Bitbucket through natural language commands",
        backstory=(
            "You are an expert assistant with access to Bitbucket tools. "
            "You can perform various Bitbucket operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Bitbucket operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Bitbucket related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Bitbucket through Composio's Tool Router. The agent can perform Bitbucket operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Bitbucket MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Bitbucket MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Bitbucket MCP with Claude Agent SDK

Google ADK

Google ADK

Use Bitbucket MCP with Google ADK

LangChain

LangChain

Use Bitbucket MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Bitbucket MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Bitbucket MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Bitbucket MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Bitbucket MCP?

With a standalone Bitbucket MCP server, the agents and LLMs can only access a fixed set of Bitbucket tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bitbucket and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Bitbucket tools.

Can I manage the permissions and scopes for Bitbucket while using Tool Router?

Yes, absolutely. You can configure which Bitbucket scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Bitbucket data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free