MCP Gateway & Registry is a governed control plane that provides one authenticated entry point for MCP servers, AI agents, skills, and other AI assets, while supporting discovery, access control, and audit records. Organizations use it to register and manage development tools for autonomous agents and coding assistants. Catalogue add-ons operate or extend workflows around these registered AI assets.
Borrowing it
Nothing to install: this file belongs to agentic-community/mcp-gateway-registry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agentic-community/mcp-gateway-registry/main/AGENTS.mdgit clone --depth 1 https://github.com/agentic-community/mcp-gateway-registryWrote 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/agentic-community/mcp-gateway-registry/agents-md)<a href="https://agentmods.dev/instructions/agentic-community/mcp-gateway-registry/agents-md"><img src="https://agentmods.dev/badge/instructions/agentic-community/mcp-gateway-registry/agents-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.
<a href="https://agentmods.dev/instructions/agentic-community/mcp-gateway-registry/agents-md"><img src="https://agentmods.dev/badge/instructions/agentic-community/mcp-gateway-registry/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.15909 | $0.15909 |
| Opus 5.5 | $0.06364 | $0.06364 |
| Sonnet 5.5 | $0.03182 | $0.03182 |
| Haiku 4.5 | $0.01591 | $0.01591 |
Grade C, and why
mcp-gateway-registry AGENTS.md scanned grade C with 3 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 3d 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
metadata endpoints (AWS plus Alibaba `100.100.100.200`), including scoped/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}\n' http://localhost/health Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 1,505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Coding Rules
Overview
This document contains coding standards and best practices that must be followed for all code development. These rules prioritize maintainability, simplicity, and modern Python development practices.
Core Principles
- Write code with minimal complexity for maximum maintainability and clarity
- Choose simple, readable solutions over clever or complex implementations
- Prioritize code that any team member can confidently understand, modify, and debug
Pull Request Evaluation
When evaluating pull requests for merge, adopt the Merge Specialist persona defined in .claude/skills/pr-review/personas/merge-specialist.md. This persona provides comprehensive guidelines for:
- Running and verifying tests
- Assessing code quality against these standards
- Reviewing architecture and design decisions
- Checking for breaking changes
- Evaluating performance impact
- Ensuring documentation is complete
IMPORTANT: Before approving any PR for merge, the Merge Specialist must verify that all tests pass and no existing functionality is broken. A PR with failing tests should NEVER be approved for merge.
Python Version
pyproject.toml is the source of truth: requires-python = ">=3.14". Do not restate a
version anywhere else; read it from there.
One known inconsistency to be aware of rather than copy: [tool.ruff] target-version
is still py311, so ruff will not apply modernizations newer than 3.11 even though the
runtime is 3.14. Raising it is a small separate change; until then, expect ruff to be
more conservative than the runtime allows.
Technology Stack
Package Management
- Always use
uvandpyproject.tomlfor package management - Use
uvfor every dependency operation. Never invokepipon its own
Modern Python Libraries
- Data Processing: Use
polarsinstead ofpandas - Web APIs: Use
fastapiinstead offlask - Code Formatting/Linting: Use
rufffor both linting and formatting - Type Checking: Use
mypy- type checks have become actually useful and should be part of CI/CD - Performance: Leverage modern CPython improvements - CPython is now much faster
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.
- 3d ago Changed · +1 lines · +78 tokens per session 3229f17357bd
- 7d ago Changed · +13 lines · +215 tokens per session 08be66a908f7
- 8d ago Changed · +14 lines · +240 tokens per session dd72dab56d33
- 10d ago Changed · +20 lines · +340 tokens per session a6c6f72d0d6d
- 20d ago First seen · 1,457 lines · 15,036 tokens per session scan C ba177afb7040
mcp-gateway-registry AGENTS.md is an instructions file published in the GitHub repository agentic-community/mcp-gateway-registry (1,012 stars, last pushed today), licensed Apache-2.0. It adds 15,909 tokens to every session, about $0.0636 per session on Opus 5.5. A static security scan graded it C with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.