bitbucket-mcp: Instructions file for Claude Code

CLAUDE.md

bitbucket-mcp CLAUDE.md is an instructions file for Claude Code from lawp09/bitbucket-mcp. It costs 8,481 tokens per session, scanned B, original, MIT.

Project instructions for bitbucket-mcp, a server that lets compatible coding tools work with Bitbucket through its API. They cover setup with uvx, Docker or Podman, configuration, and common commands.

In plain words
What is it for?
Use them when installing, configuring, running, or managing the bitbucket-mcp server, including its username, API token, workspace, and container setup.
Why use it?
They provide the required settings and setup steps for connecting the server to a Bitbucket workspace. This avoids having to infer how the project is configured.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; reads ~/.codex paths.

This is lawp09/bitbucket-mcp's own configuration. It tells Claude Code how to work on bitbucket-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bitbucket-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lawp09/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/lawp09/bitbucket-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lawp09/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.

agentmods badge for bitbucket-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lawp09/bitbucket-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lawp09/bitbucket-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lawp09/bitbucket-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lawp09/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.

agentmods 80×15 button for bitbucket-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lawp09/bitbucket-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lawp09/bitbucket-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,481 This file is loaded in full into every session.
When invoked 8,481 The same file — it is already loaded in full.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08481 $0.08481
Opus 5.5 $0.03392 $0.03392
Sonnet 5.5 $0.01696 $0.01696
Haiku 4.5 $0.00848 $0.00848

Measured 10d ago against content hash 1ef6a50345f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

bitbucket-mcp CLAUDE.md scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**OpenAI Codex TOML config** (`~/.codex/config.toml`):
CLAUDE.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Bitbucket MCP Server

Project Overview

Name: bitbucket-mcp-py Type: MCP (Model Context Protocol) Server for Bitbucket API Version: 1.29.2 Python: 3.12+ Container Runtime: Podman (preferred) or Docker

Claude Code CLI:

claude mcp add bitbucket-mcp \
  -e [email protected] \
  -e BITBUCKET_TOKEN=your-api-token \
  -e BITBUCKET_WORKSPACE=your-workspace \
  -- uvx --from bitbucket-mcp-py bitbucket-mcp

Claude Code / GitHub Copilot JSON config:

{
  "mcpServers": {
    "bitbucket-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from", "bitbucket-mcp-py", "bitbucket-mcp"],
      "env": {
        "BITBUCKET_USERNAME": "[email protected]",
        "BITBUCKET_TOKEN": "your-api-token",
        "BITBUCKET_WORKSPACE": "your-workspace"
      }
    }
  }
}

OpenAI Codex TOML config (~/.codex/config.toml):

[mcp_servers.bitbucket-mcp]
command = "uvx"
args = ["--from", "bitbucket-mcp-py", "bitbucket-mcp"]
env = { BITBUCKET_USERNAME = "[email protected]", BITBUCKET_TOKEN = "your-api-token", BITBUCKET_WORKSPACE = "your-workspace" }

Note: The PyPI package is bitbucket-mcp-py but the command entry point is bitbucket-mcp. The --from flag is required with uvx.

Quick Commands

# Container management (uses podman or docker automatically)
make build          # Build container image
make up             # Start container
make down           # Stop container
make verify         # Test Bitbucket authentication
make test           # Run tests locally
make logs           # Show container logs
make clean          # Remove container and image

# Execute MCP server
podman exec -i bitbucket-mcp python -m src.main --transport stdio

Project Structure

src/
├── main.py              # CLI entry point (stdio/HTTP transport)
├── server.py            # MCP server, tool registration
├── client.py            # BitbucketClient (async, Basic Auth)
└── utils/
    ├── credentials.py   # Secure credentials (env vars + keychain)
    ├── pagination.py    # Pagination utilities (max_pages, max_items)
    └── transformers.py  # Slim response transformers (reduce LLM token usage)

configs/
└── tools.json           # Tool enable/disable configuration

.github/workflows/
├── ci.yml               # CI pipeline (tests, chart lint, image smoke test, chart publish check, build)
└── release.yml          # Release pipeline (PyPI + MCP Registry + GHCR image + Helm chart + GitHub Release)

charts/bitbucket-mcp/    # Helm chart (multi-tenant HTTP); examples/k3s-traefik.yaml, examples/gke.yaml

docs/
├── deployment-kubernetes.md  # Kubernetes deployment guide
└── deployment-modes.md       # Deployment modes and threat model (stdio, HTTP single/multi-tenant)

tests/                   # pytest test suite (incl. tests/test_helm_chart.py)
scripts/                 # Shell scripts (build.sh, run.sh)
server.json              # MCP Registry server manifest

Read the full file on GitHub · 346 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.

  1. 10d ago Changed · +1 lines · +243 tokens per session 1ef6a50345f3
  2. 29d ago Changed · +2 lines · +307 tokens per session cb27baa09793
  3. 1mo ago Changed · +14 lines · +844 tokens per session 8e1c07ba77dc
  4. 1mo ago Changed · +1 lines · +450 tokens per session 874a9d0dabd7
  5. 2mo ago First seen · 328 lines · 6,637 tokens per session scan B 60e84c491d2b

Subscribe to this mod's changes

bitbucket-mcp CLAUDE.md is an instructions file published in the GitHub repository lawp09/bitbucket-mcp (3 stars, last pushed 11d ago), licensed MIT. It adds 8,481 tokens to every session, about $0.0339 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

bitbucket-mcp CLAUDE.md compared with instructions from other repositories

bitbucket-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
bitbucket-mcp CLAUDE.mdlawp09/bitbucket-mcpInstructions file311d agoMITB8,481Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode