MCP Bitbucket Server
Enables automated interaction with Bitbucket, including creating and listing pull requests, through the Model Context Protocol.
README
MCP Bitbucket Server
An MCP (Model Context Protocol) server to interact with Bitbucket through automated tools.
Installation
1. Clone the repository
git clone <repository-url>
cd bitbucket
2. Install dependencies
Option A: With pnpm (recommended)
pnpm install
Option B: With npm
npm install
3. Configure environment variables
Create a .env file in the project root with your Bitbucket credentials:
BITBUCKET_EMAIL=your_email@example.com
BITBUCKET_API_TOKEN=your_api_token
BITBUCKET_WORKSPACE=your_workspace
BITBUCKET_REVIEWER_UUID=reviewer_uuid_optional
BITBUCKET_API_BASE_URL=https://api.bitbucket.org/2.0
BITBUCKET_DEFAULT_DESTINATION_BRANCH=develop
BITBUCKET_CLOSE_SOURCE_BRANCH=true
Variable descriptions:
BITBUCKET_EMAIL: Your Bitbucket account emailBITBUCKET_API_TOKEN: Your Bitbucket App Password (not your regular password)BITBUCKET_WORKSPACE: Your Bitbucket workspace nameBITBUCKET_REVIEWER_UUID: (Optional) UUID of a default reviewer for pull requestsBITBUCKET_API_BASE_URL: (Optional) Base URL for Bitbucket API (default: https://api.bitbucket.org/2.0)BITBUCKET_DEFAULT_DESTINATION_BRANCH: (Optional) Default destination branch for pull requests (default: develop)BITBUCKET_CLOSE_SOURCE_BRANCH: (Optional) Whether to close source branch after merge (default: true)
MCP Configuration
Add the following configuration to your MCP settings file (usually in ~/.config/mcp/settings.json or similar):
{
"mcpServers": {
"bitbucket": {
"command": "npx",
"args": ["tsx", "/full/path/to/project/src/server.ts"],
"env": {
"BITBUCKET_EMAIL": "your_email@example.com",
"BITBUCKET_API_TOKEN": "your_api_token",
"BITBUCKET_WORKSPACE": "your_workspace",
"BITBUCKET_REVIEWER_UUID": "reviewer_uuid_optional",
"BITBUCKET_API_BASE_URL": "https://api.bitbucket.org/2.0",
"BITBUCKET_DEFAULT_DESTINATION_BRANCH": "develop",
"BITBUCKET_CLOSE_SOURCE_BRANCH": "true"
}
}
}
}
Note: Replace /full/path/to/project with the absolute path where you have cloned this project.
Usage
Once configured, you can use the following tools from your MCP client:
- Create Pull Request: Automatically create pull requests
- List Pull Requests: View all pull requests in the repository
- Prepare Pull Request: Automatically generate titles and descriptions for pull requests
Development
To run the server in development mode:
With pnpm:
pnpm run inspector
With npm:
npm run inspector
Requirements
- Node.js 18+
- pnpm or npm
- Bitbucket account with App Password configured
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.