Bitbucket MCP
MCP server for Bitbucket Cloud, focused on pull-request review workflows
README
bitbucket-mcp
English · Português (BR)
MCP server for Bitbucket Cloud, focused on the first pass of pull-request review. stdio transport, for use with Claude Code or Claude Desktop.
Why an API token (and not an app password)
Bitbucket Cloud app passwords have been in brownout since 2026-06-09 and are removed on 2026-07-28. This server uses an API token, and the HTTP Basic pair is email:token — the Bitbucket REST API requires the Atlassian account email, not the username. Using the username results in a silent 401.
1. Create the API token
- Bitbucket top bar → Settings → Atlassian account settings → Security.
- Create and manage API tokens → Create API token with scopes.
- Name it, set an expiry, and select Bitbucket as the app.
- Minimum scopes for PR review:
read:repository:bitbucket(read repositories, diffs, files)read:pullrequest:bitbucket(read PRs and comments)write:pullrequest:bitbucket(comment, approve, request changes)
- Copy the token (shown only once).
2. Install and build
npm install
npm run build
This generates dist/index.js (the server binary).
3. Configure in Claude Code
Add this to the project's .mcp.json (or to your global Claude Code config):
{
"mcpServers": {
"bitbucket": {
"command": "node",
"args": ["/absolute/path/to/bitbucket-mcp/dist/index.js"],
"env": {
"BITBUCKET_EMAIL": "your-email@domain.com",
"BITBUCKET_API_TOKEN": "your_api_token",
"BITBUCKET_WORKSPACE": "your_workspace"
}
}
}
}
Alternative, via the CLI:
claude mcp add bitbucket \
-e BITBUCKET_EMAIL=your-email@domain.com \
-e BITBUCKET_API_TOKEN=your_api_token \
-e BITBUCKET_WORKSPACE=your_workspace \
-- node /absolute/path/to/bitbucket-mcp/dist/index.js
BITBUCKET_WORKSPACE is optional; if omitted, each tool must be given workspace explicitly.
Tools
Read (no side effects):
| Tool | Purpose |
|---|---|
list_repositories |
Repositories in the workspace |
list_pull_requests |
PRs by state (OPEN/MERGED/DECLINED/SUPERSEDED) |
get_pull_request |
PR metadata (description, branches, reviewers, approvals) |
get_pull_request_diff |
Unified diff — the basis for the review |
get_pull_request_comments |
Existing comments (general and inline) |
get_pull_request_commits |
PR commits |
list_directory |
Lists the repo file tree at a commit/branch (explore the project) |
get_file |
Contents of a file (default branch if commit is omitted) |
Write (mutate state in Bitbucket):
| Tool | Purpose |
|---|---|
add_pull_request_comment |
Comment on the PR; path + line together = inline |
approve_pull_request |
Approve the PR |
request_changes_pull_request |
Mark "request changes" |
Security note
The token grants read/write access to the workspace's PRs. Treat it as a secret: keep it in an environment variable / secret manager, and never commit it. For a first-pass subagent that only suggests review without mutating anything, use a read-only scoped token — that way approve/comment fail on permission rather than relying on prompt discipline.
License
MIT © José Danilo
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.