Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/ttekun/bitbucket-cloud-mcp-server/agents-mdgit clone --depth 1 https://github.com/ttekun/bitbucket-cloud-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/ttekun/bitbucket-cloud-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/ttekun/bitbucket-cloud-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ttekun/bitbucket-cloud-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
bitbucket-cloud-mcp-server AGENTS.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 4d 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.
What it actually says
Agent Guidelines for Bitbucket Cloud MCP Server
Commands
- Build:
npm run build(compiles TypeScript to build/) - Test:
npm test(runs all Jest tests) - Test single file:
npm test -- path/to/test.test.ts - Lint:
npm run lint - Dev watch:
npm run dev(watches for TypeScript changes) - Start:
npm start(runs the built MCP server) - Inspector:
npm run inspector(MCP debugging tool)
Architecture
- MCP Server: Node.js MCP server for Bitbucket Cloud API integration (read-only)
- Main entry: src/index.ts (executable MCP server using @modelcontextprotocol/sdk)
- Services: src/services/BitbucketCloudService.ts (encapsulates Bitbucket API calls)
- Tests: src/tests/ (Jest tests with ts-jest preset, tests in /tests//*.test.ts pattern)
- API: Bitbucket Cloud REST API v2.0 via axios with Bearer token authentication
- Logging: Winston logger writing to bitbucket-cloud.log
- Config: Environment variables via dotenv (BITBUCKET_TOKEN required, BITBUCKET_WORKSPACE optional)
Code Style
- Language: TypeScript with strict mode enabled
- Module system: CommonJS (target: es2020)
- Formatting: TypeScript-ESLint with @typescript-eslint/recommended rules
- Types: Prefer explicit interfaces (e.g., BitbucketConfig, PullRequestParams); no-explicit-any is warning-level
- Naming: snake_case for API params (workspace, repo_slug, pull_request_id), camelCase for TypeScript code
- Error handling: Use McpError from SDK with appropriate ErrorCode; catch and log axios errors
- Comments: Japanese comments allowed (環境変数, ロガー seen in codebase)
- Imports: Group by external packages first, then types/interfaces
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.
- 4d ago First seen · 30 lines · 431 tokens per session scan A 92fe48d2890c
bitbucket-cloud-mcp-server AGENTS.md is an instructions file published in the GitHub repository ttekun/bitbucket-cloud-mcp-server (0 stars, last pushed 5mo ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
bitbucket-cli CLAUDE.md
Claude Code instructions for avivsinai/bitbucket-cli, covering bitbucket-cli, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
bitbucket-cli AGENTS.md
AGENTS.md instructions for avivsinai/bitbucket-cli, covering agents.md and codex notes.
bitbucket-mcp CLAUDE.md
Instructions for MatanYemini/bitbucket-mcp, covering claude.md, project overview, development commands, build and run and testing and quality.
bitbucket-mcp CLAUDE.md
Instructions for lawp09/bitbucket-mcp, covering claude.md - bitbucket mcp server, project overview, client configuration (uvx — recommended), quick commands and container management (uses podman or docker automatically).
stash-mcp codebase.instructions.md
Use when working on stash-mcp codebase structure, project references, build setup, Docker, CI workflows, or the Bitbucket.Net submodule. Covers repository layout, submodule conventions, and build/test commands.
bitbucket-mcp CLAUDE.md
Claude Code instructions for or2ooo/bitbucket-mcp, covering bitbucket cloud mcp server, quick reference, environment variables, project structure and module boundaries.