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/labs64/netlicensing-mcp/agents-mdgit clone --depth 1 https://github.com/Labs64/NetLicensing-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/labs64/netlicensing-mcp/agents-md)<a href="https://agentmods.dev/instructions/labs64/netlicensing-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/labs64/netlicensing-mcp/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 | $0.02146 | $0.02146 |
| Opus 5 | $0.01073 | $0.01073 |
| Sonnet 5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
NetLicensing-MCP 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 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI Agents when working with code in this repository.
Overview
netlicensing-mcp is a FastMCP server that exposes the Labs64 NetLicensing REST API as MCP tools and prompts. It runs over stdio (Claude Desktop / Copilot) or streamable HTTP (remote deployments). Python ≥ 3.12, async throughout.
Development commands
# Install dev environment (editable + dev extras)
pip install -e ".[dev]"
pip install hatch hatch-vcs
# Run the server locally
python -m netlicensing_mcp.server # stdio (default)
python -m netlicensing_mcp.server http # HTTP on $MCP_HOST:$MCP_PORT (127.0.0.1:8000)
mcp dev src/netlicensing_mcp/server.py # MCP Inspector UI at http://localhost:5173
# Tests (pyproject sets asyncio_mode=auto and turns on coverage automatically)
pytest tests/ -v
pytest tests/test_tools.py::test_name -v # run a single test
pytest tests/ -v --no-cov # disable coverage for faster iteration
# Lint / format / type-check (these are the exact CI checks)
ruff check .
ruff format --check . # use `ruff format .` to apply
mypy src/
# Security
pip-audit --ignore-vuln CVE-2026-4539 --ignore-vuln CVE-2026-3219
# Build & Docker
hatch build --target wheel # version comes from git tag via hatch-vcs
docker build -t ghcr.io/labs64/netlicensing-mcp:latest .
CI matrix runs tests on Python 3.12, 3.13, 3.14. Lint/format/mypy run on 3.14 only.
Architecture
Three layers, top-down:
server.py— single FastMCP entry point. Each NetLicensing operation is a thin@mcp.tool()wrapper namednetlicensing_<action>_<entity>(e.g.netlicensing_create_license). The wrapper's only jobs are: (a) translate empty strings /Nonedefaults into "leave unchanged" semantics, (b) call the matching function intools/<entity>.py, (c) wrapNetLicensingErrorinto a JSON error blob via_error(). Tools return JSON strings, not dicts —_json()serializes the result and applies the redaction layer. Token create operations additionally calltag_one_time_display()before_json(); token read operations use_json_token_read()which appliesredact_token_read()to also mask APIKEYnumberand SHOPshopURLfields.
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 · 97 lines · 2,146 tokens per session scan A ebbe527a6031
NetLicensing-MCP AGENTS.md is an instructions file published in the GitHub repository Labs64/NetLicensing-MCP (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,146 tokens to every session, about $0.0107 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
python-sdk AGENTS.md
AGENTS.md instructions for modelcontextprotocol/python-sdk, covering development guidelines, note for ai agents, branching model, package management and code quality.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
Cortex CLAUDE.md
Claude Code instructions for cdeust/Cortex, covering cortex — persistent memory mcp server, problem statement, build & test, releasing and architecture.
property-shared CLAUDE.md
Claude Code instructions for paulieb89/property-shared, covering claude.md, project overview, commands, run api server and run cli (core mode - no server needed).
ros2_mcp AGENTS.md
AGENTS.md instructions for wise-vision/ros2_mcp, covering agent instructions, project layout, dev setup (preferred), running locally and tests.
python-sdk CLAUDE.md
Claude Code instructions for modelcontextprotocol/python-sdk, a project described as: The official Python SDK for Model Context Protocol servers and clients.