bitbucket-data-center-mcp
MCP server for Bitbucket Data Center that enables PR creation, review comment management, and rebasing workflows through natural language commands.
README
bitbucket-data-center-mcp
A Model Context Protocol (MCP) server for Bitbucket Data Center, designed to improve developer productivity.
Prerequisites
Environment Variables
| Variable | Required | Description |
|---|---|---|
BITBUCKET_URL |
Yes | Base URL of your Bitbucket Data Center instance (e.g. https://bitbucket.example.com) |
BITBUCKET_TOKEN |
Yes | Personal access token for authentication |
DEBUG |
No | Set to any value to enable debug logging |
Installation
git clone https://github.com/peterknezek/bitbucket-data-center-mcp.git
cd bitbucket-data-center-mcp
pnpm install
Available Tools
| Name | Description |
|---|---|
get_pr_comments |
Fetches all unresolved inline review comments for the open PR on the current branch, including full reply threads rendered as nested trees. Pass repoPath (from git rev-parse --show-toplevel) to auto-detect project, repo, and branch via git and enable clickable file links in Cursor. |
create_pull_request |
Creates a pull request on Bitbucket Data Center. Auto-detects project, repo, and branch from repoPath. Auto-generates a PR title from branch naming convention (<type>/<taskId>_<description>), resolves the default target branch, validates that the branch has been pushed, and optionally adds reviewers and draft status. |
reply_to_pr_comment |
Posts a reply to a specific pull request comment by its ID. Use the comment IDs returned by get_pr_comments. Useful for acknowledging a review comment or explaining what fix was applied. Pass repoPath (from git rev-parse --show-toplevel) to auto-detect project, repo, and branch. |
Available Prompts
| Name | Description |
|---|---|
review-pr-comments |
Fetches and displays all unresolved PR review comments as formatted, navigable links |
create-pull-request |
Analyzes the current branch, drafts a PR title and short description following branch naming conventions, confirms with the user, then creates the pull request on Bitbucket Data Center. |
rebase-onto-main |
Detects the default branch (main or master), fetches the latest changes, rebases the current branch onto it, resolves any conflicts, and force-pushes. |
Connecting to an MCP Client
Cursor
- Open Cursor settings (Cmd/Ctrl + ,)
- Navigate to Tools & MCP → Installed MCP Server
- Add the following to your
mcp.json:
{
"mcpServers": {
"bitbucket-data-center-mcp": {
"command": "npm",
"args": ["--silent", "--prefix", "/path/to/bitbucket-data-center-mcp", "run", "dev"],
"env": {
"BITBUCKET_URL": "https://bitbucket.example.com",
"BITBUCKET_TOKEN": "your-personal-access-token"
}
}
}
}
Note: Replace /path/to/bitbucket-data-center-mcp with the actual path to this repository on your system.
Claude Desktop
- Open your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
- Add the following to the
mcpServerssection:
{
"mcpServers": {
"bitbucket-data-center-mcp": {
"command": "npm",
"args": ["--silent", "--prefix", "/path/to/bitbucket-data-center-mcp", "run", "dev"],
"env": {
"BITBUCKET_URL": "https://bitbucket.example.com",
"BITBUCKET_TOKEN": "your-personal-access-token"
}
}
}
}
Note: Replace /path/to/bitbucket-data-center-mcp with the actual path to this repository on your system.
For Developers
Scripts
| Command | Description |
|---|---|
pnpm dev |
Run the MCP server |
pnpm test |
Run tests |
pnpm typecheck |
Type-check the project |
pnpm inspect |
Launch MCP Inspector UI |
Debugging with MCP Inspector
The project includes @modelcontextprotocol/inspector as a dev dependency. Use it to interactively test tools, resources, and prompts exposed by the server.
Start the inspector:
pnpm inspect
The UI opens at http://localhost:6274.
Connect to the server in the UI:
| Field | Value |
|---|---|
| Transport | STDIO |
| Command | tsx |
| Arguments | src/index.ts |
Click Connect. The inspector spawns the server process and proxies the MCP protocol.
Alternatively, pass the command directly on the CLI:
npx @modelcontextprotocol/inspector tsx src/index.ts
Environment variables: Set BITBUCKET_URL and BITBUCKET_TOKEN in the Environment Variables section of the inspector UI before clicking Connect.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.