mcp-sentinel: Instructions file for Claude Code

CLAUDE.md

mcp-sentinel CLAUDE.md is an instructions file for Claude Code from kirandevihosur74/mcp-sentinel. It costs 1,016 tokens per session, scanned A, original, MIT.

A set of instructions for an AI coding assistant working on a project that audits MCP servers, which are extensions that provide tools to AI systems. The project collects servers, inspects them in isolated environments, evaluates them, and proposes approved-list changes.

In plain words
What is it for?
Guiding work on the mcp-sentinel project, including its TypeScript code, server-audit process, sandbox use, and approval-gated changes.
Why use it?
It gives the coding assistant project rules for safe testing, approvals, branches, pull requests, and code structure.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents.

This is kirandevihosur74/mcp-sentinel's own configuration. It tells Claude Code how to work on mcp-sentinel 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 mcp-sentinel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kirandevihosur74/mcp-sentinel. 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/kirandevihosur74/mcp-sentinel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kirandevihosur74/mcp-sentinel

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 mcp-sentinel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kirandevihosur74/mcp-sentinel/claude-md/github.svg)](https://agentmods.dev/instructions/kirandevihosur74/mcp-sentinel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kirandevihosur74/mcp-sentinel/claude-md"><img src="https://agentmods.dev/badge/instructions/kirandevihosur74/mcp-sentinel/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 mcp-sentinel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kirandevihosur74/mcp-sentinel/claude-md"><img src="https://agentmods.dev/badge/instructions/kirandevihosur74/mcp-sentinel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,016 This file is loaded in full into every session.
When invoked 1,016 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01016 $0.01016
Opus 5 $0.00508 $0.00508
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00102 $0.00102

Measured 11d ago against content hash 7e3bfb3242c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-sentinel 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 11d 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.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project rules for the coding assistant working in mcp-sentinel. Read README.md first for what we are building.

What this is

An agent on TrueForge that audits MCP servers: scrape registries (Bright Data), inspect each server in a Daytona sandbox (subagents), judge, then open approval-gated PRs against allowlist.json. See README.md for the four stages and the demo script.

Rules

  • TypeScript everywhere. Node 22+.
  • The harness does the loop, tool calls, subagents, sandbox, approvals and sessions. Do not reimplement any of that. If something feels like plumbing, check whether TrueForge already does it.
  • Third-party MCP server code runs only inside the Daytona sandbox. Never npm install or execute a server under audit on the host.
  • Every action with external effect (PR, abuse report) goes through a TrueForge approval. No exceptions, including in tests.
  • Work on branches. Open a PR for every change. Qodo reviews it. Fix High findings before merge.
  • Commit messages are imperative ("Add canary check", not "Added canary check").
  • Keep files small and single-purpose. A hackathon repo that reads like real software is the Qodo track.

Bright Data scraper configuration

All web data goes through Bright Data. Never use plain fetch against a registry.

CLI is installed and authenticated (bdata config must succeed). Zone: cli_unlocker.

Registries

Registry Listing URL pattern Fields we need
npm https://www.npmjs.com/package/<name> version, published date, maintainers, weekly downloads, repo URL
Smithery https://smithery.ai/server/<owner>/<name> version, tools list (name + description), repo URL, install count
Glama https://glama.ai/mcp/servers/<id> tools list, repo URL, last updated
mcp.so https://mcp.so/server/<name> description, repo URL, tags

Start with npm and Smithery. Add the others only if both are solid.

Collectors (Scraper Studio)

Create one collector per registry from a plain-English description, then record the collector_id here so it is reused and version-controlled:

Read the full file on GitHub · 95 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. 11d ago First seen · 95 lines · 1,016 tokens per session scan A 7e3bfb3242c0

Subscribe to this mod's changes

mcp-sentinel CLAUDE.md is an instructions file published in the GitHub repository kirandevihosur74/mcp-sentinel (0 stars, last pushed 13d ago), licensed MIT. It adds 1,016 tokens to every session, about $0.0051 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens