bitbucket-mcp
Enables LLMs to review Bitbucket pull requests with custom checklists and API token authentication.
README
MCP Bitbucket Review Server
This is an MCP server for LLMs to use capabilities of bitbucket to it's code review workflows.
Installation
[!IMPORTANT]
You need python 3.10 or above for this to work.
Install from pip:
pip install mcp-bitbucket-review
Configuration in Cursor
-
Go to
File->Preferences->Cursor Settings->MCP & Integrations. -
Add a new MCP server.
-
Add the bitbucket server MCP from the following to the mcpServers object of mcp.json:
{ "mcpServers": { // ... your rest of the MCP servers "bitbucket": { "command": "mcp-bitbucket-review-server", "env": { "BITBUCKET_EMAIL": "YOUR_BITBUCKET_EMAIL", "BITBUCKET_API_TOKEN": "YOUR_BITBUCKET_API_TOKEN" } } } } -
Save the settings.
Usage sample
Open new chat and give following prompt:
Review pull request <YOUR_PULL_REQUEST_URL>
Code Review Checklist
You can provide a custom code review checklist to be used during the review process. The checklist is read from a file and can have both general guidelines and guidelines specific to each repository.
Checklist file structure
The checklist file is a plain text file with sections for each repository. A section starts with the repository name in square brackets (e.g., [my-repo]). A special section named [general] can be used for guidelines that apply to all repositories.
Here is an example of a checklist file:
[general]
Ensure code is well-documented.
Check for any commented-out code that should be removed.
[my-awesome-repo]
Follow the "Awesome Repo" coding style.
Make sure to update the `awesome-spec.json` file.
[another-repo]
All new features must be covered by integration tests.
Configuration
To use the checklist, you need to set the BITBUCKET_CODE_REVIEW_CHECKLIST environment variable to the absolute path of your checklist file.
You can add this to your mcp.json configuration file:
{
"mcpServers": {
// ... your rest of the MCP servers
"bitbucket": {
"command": "mcp-bitbucket-review-server",
"env": {
// ... other environment variables
"BITBUCKET_CODE_REVIEW_CHECKLIST": "C:\\path\\to\\your\\checklist.txt"
}
}
}
}
Get API token from bitbucket
-
Go to https://id.atlassian.com/manage-profile/security/api-tokens
-
Click on button labelled
Create API token with scopes -
Give scopes and store the API token. Make sure you give the following scopes to the API token:
read:pullrequest:bitbucket write:pullrequest:bitbucket read:repository:bitbucket
Happy coding!
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。