Atlassian Bitbucket MCP
Enables interaction with Bitbucket through the Model Context Protocol, allowing users to manage pull requests, add comments, review code, create tasks, and perform other repository operations using natural language.
README
atlacp
An MCP (Model Context Protocol) interface for Bitbucket.
Features
Supported tools
bitbucket_add_pr_comment- add a comment to a pull requestbitbucket_approve_pr- approve a pull requestbitbucket_create_pr- create a pull requestbitbucket_create_pr_task- create a task on a pull requestbitbucket_get_file_content- get the content of a file in a pull requestbitbucket_get_pr_diff- get the diff of a pull requestbitbucket_get_pr_diffstat- get the diffstat of a pull requestbitbucket_list_pr_tasks- list tasks on a pull requestbitbucket_merge_pr- merge a pull requestbitbucket_read_pr- read a pull requestbitbucket_request_pr_changes- request changes on a pull requestbitbucket_update_pr- update a pull requestbitbucket_update_pr_task- update a task on a pull request
Supported transports
- Streamable HTTP (default)
- SSE
- STDIO
Quick Start
See detailed version here
Configure accounts
The tool is designed to be running locally on developer's machine. In order to run the tool you need to configure your Atlassian accounts first. For bitbucket you need to create a personal access token that can read and write to the repository.
Example accounts-config.json file:
{
"accounts": [
{
"name": "user",
"default": true,
"bitbucket": { "type": "Basic", "value": "ATBBxxxxxxxxxxxxxxxx" }
}
]
}
You may optionally configure multiple accounts for different roles or different workspaces, for example you may have user and bot accounts. See quick-start/atlassian-accounts-stub.json for more details.
More on Atlassian tokens:
- Personal API Tokens (keep in mind to create a basic token for API use). When using personal access tokens, all requests will be made on behalf of the user.
- Bitbucket Access Tokens - good for bots and other automation tools.
Start the MCP server
Start docker container pointing on the atlassian-accounts.json file:
docker run -d --name atlacp-mcp \
--restart=always \
-p 8080:8080 \
-v $(pwd)/atlassian-accounts.json:/app/atlassian-accounts.json \
ghcr.io/gemyago/atlacp-mcp:latest \
-a /app/atlassian-accounts.json \
http
Integrate AI tools
Cursor MCP config (.cursor/mcp.json) section may look like this:
{
"mcpServers": {
"Atlassian MCP": {
"url": "http://localhost:8080"
}
}
}
Once configured, try to send a prompt to the editor, similar to below:
Check pull request 12345 from bitbucket repo owner/repo-name
You should see a response with PR details.
Pick appropriate transport
Root url will serve Streamable HTTP transport. You can use SSE transport by appending /sse to the root url. Example:
http://localhost:8080- Streamable HTTP transporthttp://localhost:8080/sse- SSE transport
STDIO is supported as well. Use docker run with stdio subcommand instead of http to use it.
License
MIT
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。