@jestay/bitbucket-mcp

@jestay/bitbucket-mcp

MCP server for code review of Bitbucket Cloud pull requests: list PRs, read diffs, file contents and comments, and post review comments.

Category
访问服务器

README

@jestay/bitbucket-mcp

MCP server for code review of Bitbucket Cloud pull requests: list PRs, read diffs, file contents and comments, and post review comments (general, inline on specific lines, or replies).

Tools

Tool Description
list_pull_requests List PRs of a repo, filtered by state (default OPEN)
get_pull_request Full PR metadata: branches, commits, reviewers, approval status
get_pull_request_diff Unified diff of the PR (plain text)
get_file_content Raw file content at a branch/tag/commit
list_pull_request_comments Existing PR comments (general and inline)
create_pull_request_comment Post a comment: general, inline (file_path + line) or reply (parent_id)

Review workflow

By default the server ships MCP instructions telling the connected agent to review first and comment later: read the diff, consolidate all findings, present them to the user, and post only the comments the user explicitly approved. create_pull_request_comment carries the same warning in its description.

For unattended use (automation/CI), set BITBUCKET_YOLO=true to remove the approval gate and let the agent comment autonomously.

Requirements

  • Node.js 20.6+
  • An Atlassian API token (see below)

Creating the API token

Create an API token with scopes at https://id.atlassian.com/manage-profile/security/api-tokens, select Bitbucket as the app, and grant these scopes:

Scope Used for
read:user:bitbucket Authentication / identifying the token's user
read:workspace:bitbucket Resolving the workspace in API routes
read:repository:bitbucket Reading repository file contents (get_file_content)
read:pullrequest:bitbucket Listing and reading PRs, diffs and comments
write:pullrequest:bitbucket Posting review comments

No other scopes are needed — in particular, write:repository:bitbucket is NOT required (this server never pushes code).

Note: Atlassian App Passwords are deprecated — use API tokens.

Usage (npx)

No installation needed — any machine with Node 20.6+ can run it via npx.

.mcp.json (Claude Code) or claude_desktop_config.json (Claude Desktop):

{
  "mcpServers": {
    "bitbucket": {
      "command": "npx",
      "args": ["-y", "@jestay/bitbucket-mcp"],
      "env": {
        "BITBUCKET_EMAIL": "you@company.com",
        "BITBUCKET_API_TOKEN": "your_token_here",
        "BITBUCKET_WORKSPACE": "your-workspace"
      }
    }
  }
}

Or with the Claude Code CLI:

claude mcp add bitbucket \
  -e BITBUCKET_EMAIL=you@company.com \
  -e BITBUCKET_API_TOKEN=your_token_here \
  -e BITBUCKET_WORKSPACE=your-workspace \
  -- npx -y @jestay/bitbucket-mcp

Environment variables

Variable Required Description
BITBUCKET_EMAIL Yes Atlassian account email
BITBUCKET_API_TOKEN Yes Atlassian API token (scopes above)
BITBUCKET_WORKSPACE No Default workspace so tools don't need it per call
BITBUCKET_YOLO No Set to true/1 to disable the ask-before-commenting guidance (automation/CI)

Local development

pnpm install
pnpm build
cp .env.example .env   # then fill in the values
pnpm dev               # run from source (tsx)
pnpm start             # run the compiled build

pnpm dev and pnpm start load environment variables from a .env file in the project root. When registering the server in an MCP client, environment variables come from the client's own config instead and no .env file is needed. To register a local build, use node /absolute/path/to/bitbucket-mcp/dist/index.js as the command.

Project layout

src/
├── index.ts     # entry point
├── config.ts    # env-var configuration
├── client.ts    # HTTP client for the Bitbucket Cloud API 2.0 (auth lives here)
└── server.ts    # McpServer + tool registration

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