Atlassian Bitbucket MCP Server
@aashari
关于 Atlassian Bitbucket MCP Server
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-atlassian-bitbucket": {
"command": "npx",
"args": [
"-y",
"@aashari/mcp-server-atlassian-bitbucket",
"get",
"--path",
"/workspaces"
]
}
}
}工具
6GET any Bitbucket API endpoint (read data)
POST to any endpoint (create resources)
PUT to any endpoint (replace resources)
PATCH any endpoint (partial updates)
DELETE any endpoint (remove resources)
Clone a repository locally
概览
What is Atlassian Bitbucket MCP Server?
Atlassian Bitbucket MCP Server connects AI assistants like Claude and Cursor AI directly to Bitbucket Cloud repositories, pull requests, and code. It allows developers, team leads, and DevOps engineers to interact with Bitbucket using natural language for code reviews, repository management, and workflow automation.
How to use Atlassian Bitbucket MCP Server?
Configure your MCP-compatible AI assistant to run npx -y @aashari/mcp-server-atlassian-bitbucket with environment variables for authentication. For Claude Desktop, add the server configuration to ~/.claude/claude_desktop_config.json. Set credentials via ATLASSIAN_USER_EMAIL plus ATLASSIAN_API_TOKEN (recommended) or ATLASSIAN_BITBUCKET_USERNAME plus ATLASSIAN_BITBUCKET_APP_PASSWORD. Optionally set BITBUCKET_DEFAULT_WORKSPACE in a config file at ~/.mcp/configs.json.
Key features of Atlassian Bitbucket MCP Server
- Provides 6 generic tools (
bb_get,bb_post,bb_put,bb_patch,bb_delete,bb_clone) for Bitbucket API access - Supports TOON output format reducing token consumption by 30-60% vs JSON
- Includes JMESPath (
jq) filtering to extract specific data and reduce costs - Supports branching, commits, pull requests, diffs, comments, approvals, and merges
- Offers scoped API token (future-proof) and legacy app password authentication methods
- Works with any MCP-compatible client including Claude Desktop, Cursor AI, Continue.dev, and Cline
Use cases of Atlassian Bitbucket MCP Server
- Ask AI about latest commits, open pull requests, or repository details in natural language
- Automate code reviews by having AI analyze PR diffs and add comments
- Manage pull requests—create, approve, merge, decline, or request changes via conversation
- Generate quick insights into project status, branch activity, and deployment pipelines
FAQ from Atlassian Bitbucket MCP Server
What are the runtime requirements?
Node.js 18.0.0 or higher and a Bitbucket Cloud account (not Bitbucket Server/Data Center).
How do I authenticate?
Use a scoped API token (recommended, future-proof) or an App Password (legacy, deprecated by June 2026). For tokens, set ATLASSIAN_USER_EMAIL and ATLASSIAN_API_TOKEN. For app passwords, set ATLASSIAN_BITBUCKET_USERNAME and ATLASSIAN_BITBUCKET_APP_PASSWORD.
What APIs and endpoints are available?
All Bitbucket Cloud REST API 2.0 endpoints are accessible. Common paths include workspaces, repositories, branches, commits, pull requests, diffs, comments, approvals, merges, issues, pipelines, and deployments.
How is this different from alternatives?
Generic tools give access to any Bitbucket API endpoint without being locked to predefined actions. TOON output format and JMESPath filtering reduce token costs significantly compared to raw JSON responses.
Does the server support local cloning?
Yes, the bb_clone tool allows cloning a repository locally by specifying workspaceSlug, repoSlug, and targetPath.
版本控制 分类下的更多 MCP 服务器

Github
modelcontextprotocolModel Context Protocol Servers
MCP Git Ingest
adhikaspA Model Context Protocol (MCP) server that helps read GitHub repository structure and important files.
Linear MCP Server
clinea private MCP server for accessing Linear

Git
modelcontextprotocolModel Context Protocol Servers
AIO-MCP Server
athapong🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from https://github.com/nguyenvanduocit/all-in-one-model-context-protocol
评论