About Bitbucket Server MCP
Bitbucket Server MCP is an MCP server for teams automating Bitbucket Server repository and pull request work. It supports pull request lifecycle actions, reviews, comments, and diffs, including large diffs.
Key features
- 01List repositories, branches, and pull requests
- 02Create, update, merge, decline, and delete pull requests
- 03Add comments and inline code suggestions
- 04Retrieve diffs and review status
- 05Handle large pull request diffs
Use cases
- 01Listing project repositories and branches
- 02Automating pull request creation and merging
- 03Reviewing diffs and adding inline suggestions
MCP support
It exposes Bitbucket Server repository and pull request operations as tools for MCP clients, including review and diff retrieval.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBitbucket Server MCP
A professional Model Context Protocol (MCP) server for Bitbucket Server, enabling seamless automation and integration for pull request management, code review, and repository operations.
Table of Contents
- Overview
- Features
- Installation
- Quick Start
- MCP Server Configuration
- Environment Variables
- Development
- Testing
- Contributing
- License
Overview
Bitbucket Server MCP provides a robust interface for automating and managing Bitbucket Server repositories and pull requests via the Model Context Protocol. Designed for enterprise environments, it supports advanced workflows, large diffs, and seamless integration with MCP clients.
Features
- List repositories, branches, and pull requests
- Create, update, and merge pull requests (merge-commit, squash, fast-forward)
- Decline and delete pull requests
- Add comments and inline code suggestions
- Retrieve pull request diffs and review status
- Efficient handling of large pull request diffs
- Extensible tool handler wiring for MCP protocol
- Cross-platform support (Windows, Mac, Linux)
Installation
Using npx (Recommended)
Run directly without cloning:
npx -y bitbucket-server-mcp
Local Installation
Clone and build the project:
git clone https://github.com/your-org/bitbucket-server-mcp.git
cd bitbucket-server-mcp
npm install
npm run build
Quick Start
-
Copy
.env.exampleto.envand configure your Bitbucket Server credentials. -
Start the MCP server:
npm start # or node build/index.js
🚀 MCP Server Configuration
Add the following to your MCP configuration (e.g., cline_mcp_settings.json):
{
"servers": [
{
"name": "bitbucket-server-mcp",
"command": "npx",
"args": ["-y", "bitbucket-server-mcp"],
"env": {
"BITBUCKET_URL": "https://your-bitbucket-server",
"BITBUCKET_TOKEN": "your-access-token",
"BITBUCKET_DEFAULT_PROJECT": "your-default-project",
"BITBUCKET_DEFAULT_REVIEWERS": "user1,user2"
}
}
]
}
Direct Node Usage
If npx is unavailable, configure as follows:
- Windows:
"command": "node", "args": ["C:\\path\\to\\bitbucket-server-mcp\\build\\index.js"], - Mac/Linux:
"command": "node", "args": ["/path/to/bitbucket-server-mcp/build/index.js"],
Environment Variables
| Variable | Description | Required | Example |
|---|---|---|---|
BITBUCKET_URL | Bitbucket Server base URL | Yes | https://bitbucket.example.com |
BITBUCKET_TOKEN | Personal access token | Yes | your-access-token |
BITBUCKET_DEFAULT_PROJECT | Default project key | No | PROJKEY |
BITBUCKET_DEFAULT_REVIEWERS | Comma-separated reviewer usernames | No | user1,user2 |
BITBUCKET_USERNAME | Username (if not using token) | No | your-username |
BITBUCKET_PASSWORD | Password (if not using token) | No | your-password |
See .env.example for details.
Development
- Lint code:
npm run lint - Run in watch mode:
npm run dev
Testing
Run the test suite:
npm test
Contributing
Contributions are welcome! Please open issues or submit pull requests for new features, bug fixes, or improvements.
License
This project is licensed under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.