What are the runtime requirements?
Python 3.10+, Node.js 18+, and a Bitbucket Server instance with an access token (or username/password).
@vishn9893
基本信息
This is a MCP bridge for existing TypeScript Bitbucket MCP server in a Python UV-based API layer, essentially making UV act as a proxy/bridge.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-wrapper-bitbucket": {
"command": "docker",
"args": [
"build",
"-t",
"bitbucket-mcp-wrapper",
"."
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Mcp Server Wrapper Bitbucket is a Python-based FastAPI wrapper around a TypeScript MCP (Model Context Protocol) server for managing Bitbucket Server pull requests. It bridges the original MCP server with a modern HTTP/REST interface, exposing clean REST endpoints and auto-generated OpenAPI documentation.
Install Python dependencies with pip install -r requirements.txt, then install and build the Node.js MCP server with npm install && npm run build. Start the FastAPI server using uvicorn app.main:app --reload. Alternatively, run everything inside Docker with docker build -t bitbucket-mcp-wrapper . and docker run -p 8000:8000 bitbucket-mcp-wrapper. Configure the Bitbucket server URL and authentication via environment variables BITBUCKET_URL and BITBUCKET_TOKEN (or BITBUCKET_USERNAME + BITBUCKET_PASSWORD).
/docs)Python 3.10+, Node.js 18+, and a Bitbucket Server instance with an access token (or username/password).
Set the environment variables `BITBUCKET_URL` (your Bitbucket server URL) and `BITBUCKET_TOKEN` (your access token). Alternatively, use `BITBUCKET_USERNAME` and `BITBUCKET_PASSWORD`.
POST endpoints: `/create-pull-request`, `/get-pull-request`, `/merge-pull-request`, `/decline-pull-request`, `/add-comment`, `/get-diff`, `/get-reviews`, and `/mcp` for direct MCP protocol access.
Yes. Build the image with `docker build -t bitbucket-mcp-wrapper .` and run it with `docker run -p 8000:8000 bitbucket-mcp-wrapper`.
Apache 2.0.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Throw HTML at an API, get an unguessable URL back. Zero-config remote MCP server — your agent deploys pages, sites and CI reports in one call. Free, no signup needed.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Agent-Native Terminal

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
评论