mcp: Instructions file for Claude Code

CLAUDE.md

mcp CLAUDE.md is an instructions file for Claude Code from sirrlock/mcp. It costs 833 tokens per session, scanned A, original, MIT.

A project instruction guide for building the Sirr MCP server, which lets AI assistants access a secret vault through the Model Context Protocol. It documents the TypeScript project, its structure, and five available tools.

In plain words
What is it for?
Use it when developing, testing, formatting, or reviewing the Sirr MCP server and its secret-storage tools.
Why use it?
It gives developers a shared reference for how the server works, what it exposes, and which parts are handled outside the server.

Instructions file for Claude Code

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

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

View source ↗ sirrlock/mcp
Reuse

Borrowing it

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

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sirrlock/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sirrlock/mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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 $0.00833 $0.00833
Opus 5.5 $0.00333 $0.00333
Sonnet 5.5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 2mo ago against content hash 4d5721c2b964, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@sirrlock/mcp — Claude Development Guide

Purpose

MCP (Model Context Protocol) server for Sirr — gives AI assistants direct access to the Sirr secret vault. Published to npm as @sirrlock/mcp.

Stack

  • TypeScript, Node 18+
  • @modelcontextprotocol/sdk for MCP protocol
  • Native fetch — no axios, no node-fetch
  • @biomejs/biome for lint + format
  • Jest + ts-jest for tests

Structure

src/
├── index.ts       # MCP server entry: 5 tools, env vars (SIRR_SERVER, SIRR_TOKEN, SIRR_ORG)
└── helpers.ts     # Pure helpers: parseKeyRef, path builders, formatTtl

Tools exposed (5 total)

Tool Description
store_secret With name: org-scoped named secret (requires SIRR_ORG). Without: anonymous dead drop.
read_secret By id: public dead drop. By name: org-scoped (requires SIRR_ORG).
check_secret Metadata check without consuming a read.
share_secret Burn-after-read link via sirrlock.com. No auth needed.
audit Query the audit log.

Everything else (webhooks, keys, orgs, roles, principals) is CLI/web-only — not exposed via MCP.

Routing semantics

  • store_secret without name → POST /secrets (public dead drop). Returns {id}.
  • store_secret with name → POST /orgs/{SIRR_ORG}/secrets (org-scoped). Returns {key, id}. 409 if name exists.
  • read_secret with id → GET /secrets/{id} (public).
  • read_secret with name → GET /orgs/{SIRR_ORG}/secrets/{name} (org-scoped).
  • share_secret → POST {SIRRLOCK_URL}/api/public/secret (sirrlock.com hosted).

Key Rules

  • Never log or echo secret values in tool output
  • SIRR_ORG env var is required for named secrets (store/read by name) and audit
  • SIRR_TOKEN = master key for full access, or a principal key for org-scoped access
  • check_secret does NOT consume a read — safe to call freely
  • Tool descriptions tell Claude not to memorize or repeat retrieved secret values
  • store_secret with a name returns 409 Conflict if the name already exists

Read the full file on GitHub · 84 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. 2mo ago First seen · 84 lines · 833 tokens per session scan A 4d5721c2b964

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository sirrlock/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 833 tokens to every session, about $0.0033 per session on Opus 5.5. 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 2026-09-01.

Related

mcp CLAUDE.md compared with instructions from other repositories

mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp CLAUDE.mdsirrlock/mcpInstructions file02mo agoMITA833Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot