BitBucket-MCP-To-Review-PRs
A read-only MCP server for the Bitbucket Cloud REST API v2.0 that enables AI assistants to browse workspaces, repositories, and review pull requests.
README
BitBucket-MCP-To-Review-PRs
A read-only MCP (Model Context Protocol) server for the Bitbucket Cloud REST API v2.0. Enables AI assistants (Kiro, VS Code, Claude Desktop, etc.) to browse workspaces, repositories, and review pull requests — all without modifying anything in Bitbucket.
Features
- List workspaces and repositories
- List, view, and review pull requests
- Get PR diffs, diffstats, comments, and commits
- Parse Bitbucket PR URLs for one-shot review context
- View file contents at any commit
- Automatic pagination and rate limit handling
- Strictly read-only (GET requests only)
Prerequisites
- Bun runtime
- A Bitbucket Cloud account with an App Password
App Password Scopes
Create an App Password with these read permissions:
- Account (Read)
- Workspace membership (Read)
- Repositories (Read)
- Pull requests (Read)
Setup
git clone https://github.com/arslanismail/BitBucket-MCP-To-Review-PRs.git
cd BitBucket-MCP-To-Review-PRs
bun install
MCP Client Configuration
Add this to your MCP client config:
Kiro: .kiro/settings/mcp.json
VS Code (Copilot): .vscode/mcp.json
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"bitbucket": {
"command": "bun",
"args": ["run", "src/index.ts"],
"cwd": "/absolute/path/to/BitBucket-MCP-To-Review-PRs",
"env": {
"BITBUCKET_USERNAME": "<your-atlassian-email>",
"BITBUCKET_TOKEN": "<your-app-password>"
}
}
}
}
Important: Use your Atlassian account email as the username, not your Bitbucket username.
Available Tools
| Tool | Description | Input |
|---|---|---|
list_workspaces |
List all accessible workspaces | — |
list_repositories |
List repos in a workspace | workspace |
list_pull_requests |
List PRs (defaults to OPEN) | workspace, repo_slug, state? |
get_pull_request |
Get full PR details | workspace, repo_slug, pull_request_id |
get_pull_request_diff |
Get unified diff | workspace, repo_slug, pull_request_id |
get_pull_request_diffstat |
Get files changed summary | workspace, repo_slug, pull_request_id |
get_pull_request_comments |
Get all PR comments | workspace, repo_slug, pull_request_id |
get_pull_request_commits |
Get commits in a PR | workspace, repo_slug, pull_request_id |
get_pr_from_link |
Parse PR URL, return details + diff + diffstat | url |
get_file_contents |
Get file at a specific commit | workspace, repo_slug, commit, path |
Example Usage
Once connected, ask your AI assistant:
- "List my Bitbucket workspaces"
- "Show me open PRs in avizia/one"
- "Review this PR: https://bitbucket.org/myworkspace/myrepo/pull-requests/123"
Project Structure
src/
├── index.ts # Entry point, env validation, tool registration
├── bitbucket-client.ts # HTTP client (GET-only, auth, pagination, rate limiting)
├── types.ts # Bitbucket API response interfaces
└── tools/ # Individual tool implementations
├── list-workspaces.ts
├── list-repositories.ts
├── list-pull-requests.ts
├── get-pull-request.ts
├── get-pull-request-diff.ts
├── get-pull-request-diffstat.ts
├── get-pull-request-comments.ts
├── get-pull-request-commits.ts
├── get-pr-from-link.ts
└── get-file-contents.ts
License
MIT
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.