What is bitbucket-mcp CLAUDE.md?

Repository instructions for an MCP server. MCP is a standard way for AI assistants to call external tools; this server gives them access to Bitbucket repositories, pull requests, build pipelines, and related APIs.

Use them when changing Bitbucket integrations, TypeScript source, Jest tests, ESLint rules, the MCP Inspector setup, or npm release commands.

They document the safe development workflow and make clear how to build, run, test, lint, inspect, and publish the server without delete operations.

How MatanYemini/bitbucket-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MatanYemini/bitbucket-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MatanYemini/bitbucket-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/MatanYemini/bitbucket-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/matanyemini/bitbucket-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/matanyemini/bitbucket-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/matanyemini/bitbucket-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/matanyemini/bitbucket-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/matanyemini/bitbucket-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/matanyemini/bitbucket-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,261 This file is loaded in full into every session.

When invoked 1,261 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01261	$0.01261
Opus 5.5	$0.00504	$0.00504
Sonnet 5.5	$0.00252	$0.00252
Haiku 4.5	$0.00126	$0.00126

Measured 2mo ago against content hash 7faf76d02b46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bitbucket-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Model Context Protocol (MCP) server that provides AI assistants with programmatic access to Bitbucket Cloud and Server APIs. It's published as an npm package (bitbucket-mcp) and enables operations on repositories, pull requests, pipelines, and more through a standardized MCP interface.

Safety First: No DELETE operations are used to prevent accidental data loss. Every PR is analyzed with CodeQL for security.

Development Commands

Build and Run

npm install          # Install dependencies
npm run build        # Compile TypeScript to dist/ (also sets executable permission)
npm start            # Run compiled server from dist/index.js
npm run dev          # Run in development mode with watch (uses tsx)

Testing and Quality

npm test             # Run Jest tests
npm run lint         # Run ESLint on src/**/*.ts

MCP Inspector

npm run inspector    # Launch MCP inspector for debugging tools

Publishing

npm run publish:patch   # Bump patch version and publish
npm run publish:minor   # Bump minor version and publish
npm run publish:major   # Bump major version and publish
npm run release         # Alias for publish:patch

Architecture

Single-File Design

The entire server implementation lives in src/index.ts (~4,500 lines). This includes:

Type definitions for Bitbucket API entities
BitbucketClient class with all API methods
MCP server setup and tool registration
Logging configuration

Core Components

BitbucketClient Class: Main API wrapper that handles:

Axios-based HTTP client with authentication (token or username/password)
URL normalization (converts web URLs like bitbucket.org/workspace to API URLs)
All Bitbucket API operations grouped by category:
- Repository operations (list, get details)
- Pull request operations (CRUD, approve, merge, decline, etc.)
- PR comments (general and inline)
- PR tasks (TODO items)
- PR diffs and patches
- Pipeline operations (list, run, stop, get logs)

Read the full file on GitHub · 139 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 139 lines · 1,261 tokens per session scan A 7faf76d02b46

Subscribe to this mod's changes

bitbucket-mcp CLAUDE.md is an instructions file published in the GitHub repository MatanYemini/bitbucket-mcp (168 stars, last pushed 5mo ago), licensed MIT. It adds 1,261 tokens to every session, about $0.0050 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-tools antrophic bitbucket llm-agents mcp mcp-server

bitbucket-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bitbucket-mcp CLAUDE.mdMatanYemini/bitbucket-mcp	Instructions file	168	5mo ago	MIT	A	1,261	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bitbucket-mcp: Instructions file for Claude Code