mcp -atlassian-bitbucket
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.
claude mcp add --transport stdio aashari-mcp-server-atlassian-bitbucket npx -y @aashari/mcp-server-atlassian-bitbucket \ --env ATLASSIAN_API_TOKEN="your_scoped_api_token" \ --env ATLASSIAN_USER_EMAIL="your.email@company.com" \ --env BITBUCKET_DEFAULT_WORKSPACE="your_main_workspace" \ --env ATLASSIAN_BITBUCKET_USERNAME="your_username" \ --env ATLASSIAN_BITBUCKET_APP_PASSWORD="your_app_password"
How to use
This MCP server exposes a set of Bitbucket APIs through simple, language-agnostic commands so AI assistants can query, modify, and manage Bitbucket data using natural language prompts. With the six generic tools bb_get, bb_post, bb_put, bb_patch, bb_delete, and bb_clone, you can read data from any Bitbucket Cloud REST API endpoint, create or update resources, delete items, or clone repositories locally. You can also filter results with JMESPath queries to minimize payloads and costs. The server integrates with Claude, Cursor AI, Continue.dev, Cline, and other MCP-compatible clients, enabling you to perform common repository tasks such as listing workspaces and repositories, inspecting pull requests, and automating PR-related workflows via simple prompts like “Show me all open PRs that need review.” To configure, supply credentials using either scoped API tokens (recommended) or Bitbucket app passwords, and point your AI assistant to run the MCP server using npx or a global npm installation.
How to install
Prerequisites:\n- Node.js 18.0.0 or higher (and npm)\n- Access credentials for Bitbucket Cloud (scoped API token or app password)\n\nInstallation steps:\n1) Install Node.js (if not already installed).\n - Windows/Mash: download from https://nodejs.org/ or use a version manager.\n - macOS/Linux: use your preferred package manager (e.g., homebrew, apt).\n\n2) Run the MCP server via npx (recommended for always-latest):\nbash\nexport ATLASSIAN_USER_EMAIL="your.email@company.com"\nexport ATLASSIAN_API_TOKEN="your_scoped_api_token" # or set legacy credentials as shown in README\n\nnpx -y @aashari/mcp-server-atlassian-bitbucket get --path "/workspaces"\n\n\n3) Optional: install globally for convenience (stable version):\nbash\nnpm install -g @aashari/mcp-server-atlassian-bitbucket\n\nThen configure your AI assistant to run: bitbucket (or the configured server name) with the MCP transport.\n\n4) Configure environment variables for continued access as described in the README (scoped API tokens recommended).
Additional notes
Tips and notes:\n- Use scoped API tokens whenever possible for long-term stability and deprecation timelines.\n- If you switch credentials, update the env vars used by your MCP client configuration.\n- For Claude Desktop or other assistants, you can embed the MCP server reference in your config as shown in the README, enabling V1-compatible transports.\n- The six tools (bb_get, bb_post, bb_put, bb_patch, bb_delete, bb_clone) map to standard REST operations and Bitbucket endpoints; remember to prefix paths with /2.0 automatically.\n- When querying large data sets, leverage the jq parameter to reduce payloads and focus on fields you actually need.\n- If you encounter rate limits or authentication errors, verify token scopes and ensure the account has access to the requested workspaces/repositories.
Related MCP Servers
claude-code-open
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
boilerplate
TypeScript Model Context Protocol (MCP) server boilerplate providing IP lookup tools/resources. Includes CLI support and extensible structure for connecting AI systems (LLMs) to external data sources like ip-api.com. Ideal template for creating new MCP integrations via Node.js.
mcp -atlassian-jira
Node.js/TypeScript MCP server for Atlassian Jira. Equips AI systems (LLMs) with tools to list/get projects, search/get issues (using JQL/ID), and view dev info (commits, PRs). Connects AI capabilities directly into Jira project management and issue tracking workflows.
mcp -atlassian-confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
local-skills
Universal MCP server enabling any LLM or AI agent to utilize expert skills from your local filesystem. Reduces context consumption through lazy loading. Works with Claude, Cline, and any MCP-compatible client.
unity
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.