Bitbucket MCP Server

Bitbucket MCP Server

A Model Context Protocol server that integrates Cursor IDE with Bitbucket Cloud, allowing developers to fetch repository information and commit data directly from their Bitbucket workspace.

Category
访问服务器

README

Bitbucket MCP

A Model Context Protocol (MCP) server that integrates Cursor IDE with Bitbucket Cloud, allowing you to fetch repository information and commit data directly from your Bitbucket workspace.

Features

  • List Repositories: Fetch all repositories from your Bitbucket workspace
  • Repository Details: Get detailed information about specific repositories
  • Commit Information: Retrieve commit history and latest commit details
  • Commit Counts: Get total commit counts per repository
  • Latest Commit Data: Fetch the most recent commit date, author, and message for each repository

Prerequisites

  • Node.js 18 or higher
  • npm or yarn
  • A Bitbucket Cloud account
  • Bitbucket App Password (for authentication)

Setup

1. Install Dependencies

npm install

2. Build the Project

npm run build

3. Create Bitbucket App Password

  1. Go to your Bitbucket account settings
  2. Navigate to "App passwords" under "Access management"
  3. Click "Create app password"
  4. Give it a descriptive name (e.g., "Cursor MCP Integration")
  5. Select the following permissions:
    • Repositories: Read
    • Account: Read (optional, for user info)
  6. Copy the generated app password

4. Configure Environment Variables

Create a .env file in the project root:

BITBUCKET_USERNAME=your_bitbucket_username
BITBUCKET_APP_PASSWORD=your_app_password_from_step_3
BITBUCKET_WORKSPACE=your_workspace_name

Note: The workspace name is typically your username or organization name. You can find it in your Bitbucket URLs (e.g., https://bitbucket.org/workspace_name/).

5. Add to Cursor MCP Configuration

Add the following configuration to your Cursor MCP settings:

For macOS/Linux:

{
  "mcpServers": {
    "bitbucket": {
      "command": "node",
      "args": ["/path/to/BitbucketMCP/dist/index.js"],
      "env": {
        "BITBUCKET_USERNAME": "your_bitbucket_username",
        "BITBUCKET_APP_PASSWORD": "your_app_password",
        "BITBUCKET_WORKSPACE": "your_workspace_name"
      }
    }
  }
}

For Windows:

{
  "mcpServers": {
    "bitbucket": {
      "command": "node.exe",
      "args": ["C:\\path\\to\\BitbucketMCP\\dist\\index.js"],
      "env": {
        "BITBUCKET_USERNAME": "your_bitbucket_username",
        "BITBUCKET_APP_PASSWORD": "your_app_password",
        "BITBUCKET_WORKSPACE": "your_workspace_name"
      }
    }
  }
}

6. Restart Cursor

After adding the configuration, restart Cursor IDE to load the MCP server.

Usage

Once configured, you can use the following tools in Cursor:

1. List Repositories

List all repositories in my Bitbucket workspace

or

List repositories with commit information

2. Get Repository Details

Get details for repository "my-repo-name"

3. Get Repository Commits

Show recent commits for repository "my-repo-name"

Available Tools

list_repositories

Lists all repositories in your Bitbucket workspace.

Parameters:

  • include_commit_info (boolean, optional): Include commit count and latest commit info
  • limit (number, optional): Maximum repositories to return (default: 50, max: 100)

get_repository_commits

Gets commit history for a specific repository.

Parameters:

  • repository_name (string, required): Name of the repository
  • limit (number, optional): Maximum commits to return (default: 50, max: 100)

get_repository_details

Gets detailed information about a specific repository including latest commit data.

Parameters:

  • repository_name (string, required): Name of the repository

Development

Running in Development Mode

npm run dev

Building

npm run build

Project Structure

BitbucketMCP/
├── src/
│   └── index.ts          # Main MCP server implementation
├── dist/                 # Compiled JavaScript output
├── package.json          # Project dependencies and scripts
├── tsconfig.json         # TypeScript configuration
├── .gitignore           # Git ignore rules
└── README.md            # This file

Troubleshooting

Authentication Issues

  • Verify your Bitbucket username and app password are correct
  • Ensure the app password has the correct permissions (Repositories: Read)
  • Check that the workspace name is correct

Connection Issues

  • Verify your internet connection
  • Check if Bitbucket API is accessible from your network
  • Ensure the MCP server is running (check Cursor's MCP logs)

Repository Not Found

  • Verify the repository name is correct (use the repo slug, not display name)
  • Ensure you have access to the repository
  • Check that the repository exists in the specified workspace

MCP Server Not Loading

  • Verify the path to dist/index.js is correct in your Cursor configuration
  • Ensure Node.js is installed and accessible from the command line
  • Check Cursor's MCP server logs for error messages

Security Notes

  • Keep your Bitbucket app password secure and never commit it to version control
  • Use environment variables or secure configuration management for credentials
  • The app password should only have the minimum required permissions
  • Consider rotating your app password regularly

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

License

MIT License - see LICENSE file for details

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选