mcp-installer: Instructions file for Claude Code

CLAUDE.md

mcp-installer CLAUDE.md is an instructions file for Claude Code from joobisb/mcp-installer. It costs 2,931 tokens per session, scanned B, original, MIT.

Project instructions for an MCP installer, a tool that helps people install Model Context Protocol servers in AI clients such as Claude Desktop, Cursor, and VS Code.

In plain words
What is it for?
Use them when working on the installer's web app, command-line tool, client configuration files, or planned desktop bridge.
Why use it?
They define how the installer should hide configuration complexity while supporting different clients and limiting permissions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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-installer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joobisb/mcp-installer/claude-md.svg)](https://agentmods.dev/instructions/joobisb/mcp-installer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/joobisb/mcp-installer/claude-md"><img src="https://agentmods.dev/badge/instructions/joobisb/mcp-installer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,931 This file is loaded in full into every session.
When invoked 2,931 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02931 $0.02931
Opus 5 $0.01465 $0.01465
Sonnet 5 $0.00586 $0.00586
Haiku 4.5 $0.00293 $0.00293

Measured 7d ago against content hash a290d4b9c534, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

mcp-installer CLAUDE.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| **Gemini** | `~/.gemini/settings.json` | Direct JSON edit | ✅ Priority |
CLAUDE.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Installer Project

Project Vision

The MCP Installer is a comprehensive platform designed to solve the complexity of installing MCP (Model Context Protocol) servers across different AI clients. The goal is to create an "App Store" experience for MCPs where users can browse, discover, and install MCP servers with minimal technical knowledge.

Core Principles

  • Simplicity is Paramount: Abstract away all technical complexity
  • Client-Agnostic: Support all major MCP clients (Claude Desktop, Cursor, VS Code, etc.)
  • Trust and Security: Open-source, transparent, with minimal permissions
  • One-Click Experience: Evolve from CLI commands to true one-click installation

Technical Architecture

The Core Challenge

Web applications cannot directly access local files due to browser security sandbox. Our solution bridges this gap through a phased approach:

  1. Phase 1: CLI Companion Tool (@mcp-installer/cli)
  2. Phase 2: Web Marketplace with copy-paste commands
  3. Phase 3: Desktop Agent with custom protocol handlers

System Architecture

Web Frontend (Next.js) ↔ Local CLI Tool ↔ Client Config Files
     ↕                        ↕                ↕
MCP Server Registry     Command Generation    ~/.claude/, ~/.cursor/, etc.

Registry Distribution Architecture

The MCP Server Registry uses a hybrid approach for maximum reliability and performance:

graph TD
    A[CLI Start] --> B{Environment Check}
    B -->|Development| C[Try Local Paths]
    B -->|Production| D[Check Cache]

    C --> C1[packages/registry/servers.json]
    C --> C2[../registry/servers.json]
    C --> C3[./servers.json]
    C1 --> E[Load Successfully]
    C2 --> E
    C3 --> E
    C --> F[Local Failed] --> G[Fallback to Remote]

    D --> D1{Cache Valid?}
    D1 -->|Yes & TTL OK| E
    D1 -->|No/Expired| G

    G --> H[Fetch from GitHub Raw]
    H --> H1{Response?}
    H1 -->|200 OK| I[Parse JSON]
    H1 -->|304 Not Modified| J[Use Cache]
    H1 -->|Error| K[Try Stale Cache]

    I --> L[Save to Cache]
    L --> E
    J --> E
    K --> K1{Cache Exists?}
    K1 -->|Yes| E
    K1 -->|No| M[Final Fallback: Local]

    E --> N[Registry Ready]
    M --> O[All Failed - Error]

    style A fill:#e1f5fe
    style E fill:#c8e6c9
    style O fill:#ffcdd2
    style G fill:#fff3e0
    style L fill:#f3e5f5

Read the full file on GitHub · 332 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. 7d ago First seen · 332 lines · 2,931 tokens per session scan B a290d4b9c534

Subscribe to this mod's changes

mcp-installer CLAUDE.md is an instructions file published in the GitHub repository joobisb/mcp-installer (17 stars, last pushed 1y ago), licensed MIT. It adds 2,931 tokens to every session, about $0.0147 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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 · 7,104 tokens