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/beverage/levelang-mcp/claude-mdgit clone --depth 1 https://github.com/beverage/levelang-mcpWrote 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/beverage/levelang-mcp/claude-md)<a href="https://agentmods.dev/instructions/beverage/levelang-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/beverage/levelang-mcp/claude-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 5.1 | $0.00480 | $0.00480 |
| Opus 5 | $0.00240 | $0.00240 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
levelang-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 5d 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
Levelang MCP Server
Stateless MCP server that exposes the Levelang translation API to AI assistants (Claude, Cursor, etc.). Translates MCP tool calls into HTTP requests to the backend.
Tech Stack
- Framework: Python MCP SDK
- Package manager: uv
- Transport: stdio (local) or streamable-http (deployed)
- Deployment: Fly.io, region
cdg, port 8080
Architecture
No database, no shared state, no code shared with the backend.
src/levelang_mcp/
├── __main__.py # Entrypoint (python -m levelang_mcp)
├── server.py # MCP tools and resources definitions
├── auth.py # API-key auth middleware for HTTP transport
├── client.py # Async HTTP client for the Levelang backend API
├── config.py # Environment variable loading
├── formatting.py # API response → human-readable text for LLMs
└── logging_config.py # Logging setup
Key Coupling Points
client.py— Makes HTTP calls to the backend. Must stay in sync with backend API endpoints and response schemas.formatting.py— Formats backend JSON into human-readable text for the LLM. Must stay in sync with the backend translate response schema.server.py— Defines MCP tools (translate,translate_compare,list_languages) and resources (levelang://languages).
Configuration
| Variable | Default | Description |
|---|---|---|
LEVELANG_API_BASE_URL |
http://localhost:8000/api/v1 |
Backend URL |
LEVELANG_API_KEY |
— | Service key (sk_*) for backend auth |
MCP_TRANSPORT |
stdio |
stdio or streamable-http |
MCP_PORT |
8463 |
Port for HTTP transport |
MCP_API_KEYS |
— | Comma-separated client auth keys for HTTP |
Commands
uv sync # Install dependencies
uv run pytest tests/ -v # Run tests
git config core.hooksPath .githooks # Enable pre-commit/pre-push hooks
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.
- 5d ago First seen · 50 lines · 480 tokens per session scan A 73bfc8977f1e
levelang-mcp CLAUDE.md is an instructions file published in the GitHub repository beverage/levelang-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 480 tokens to every session, about $0.0024 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
xcstrings-crud CLAUDE.md
Claude Code instructions for Ryu0118/xcstrings-crud, covering xcstrings-crud, build & test, architecture, code style and key files.
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
DialectOS CLAUDE.md
Claude Code instructions for KyaniteLabs/DialectOS, covering kyanitelabs engineering rules, project-specific context, kyanitelabs engineering rules, organization principles and issue-driven development.
DialectOS AGENTS.md
AGENTS.md instructions for KyaniteLabs/DialectOS, covering agents.md — dialectos, public agent skill, project structure, build and testing.
KKTerm CLAUDE.md
Claude Code instructions for ryantsai/KKTerm: Constitution, Repository workflow, domain language, source-area boundaries, i18n rules, and engineering defaults live in AGENTS.md. Product terminology lives in CONTEXT.md. Read both before changing behavior or terminology.
kiwiki AGENTS.md
AGENTS.md instructions for natorus87/kiwiki, covering projekt-anweisungen, projekt-kontext, verbindliche lokalisierungsregel, regeln (automatisch geladen via .codex/rules/) and verfügbare sub-agenten.