mcp-server-manager: Instructions file for Claude Code

CLAUDE.md

mcp-server-manager CLAUDE.md is an instructions file for Claude Code, Codex from sardine-ai/mcp-server-manager. It costs 2,903 tokens per session, scanned B, a copy of mcp-server-manager AGENTS.md, MIT.

Project instructions for MCP Server Manager, a command-line and interactive tool that manages Model Context Protocol servers across AI clients.

In plain words
What is it for?
They help develop, test, lint, build, and run the manager for clients such as Claude Desktop, Cursor, Windsurf, and VS Code.
Why use it?
They explain how the project connects clients, builds the TypeScript code, and keeps configuration and running services in sync.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is sardine-ai/mcp-server-manager's own configuration. It tells Claude Code and Codex how to work on mcp-server-manager 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-server-manager configures →

Reuse

Borrowing it

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

Made for: Claude Code, Codex.

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-server-manager CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sardine-ai/mcp-server-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/sardine-ai/mcp-server-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,903 This file is loaded in full into every session.
When invoked 2,903 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 94% copy Near-identical to another mod 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 $0.02903 $0.02903
Opus 5 $0.01452 $0.01452
Sonnet 5 $0.00581 $0.00581
Haiku 4.5 $0.00290 $0.00290

Measured 9d ago against content hash ac7327021bc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

mcp-server-manager 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 9d 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.

- **Codex CLI**: `~/.codex/config.toml`
Origin

This is a copy

94% identical to mcp-server-manager AGENTS.md — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Server Manager (mcpsm) is a CLI tool for managing MCP (Model Context Protocol) servers across multiple AI clients (Claude Desktop, Cursor, Windsurf, VS Code, etc.). It provides both an interactive TUI and CLI commands for server management, testing, client syncing, and daemon control.

Client Connection Model

The system uses a gateway pattern for client connections:

  • A single mcpsm server is added to each connected client's configuration
  • This server uses supergateway to proxy all MCP requests to the daemon on localhost:{port}/mcp
  • When the port setting is changed, all connected clients are automatically updated
  • Supports real-time config loading for clients without restart (Cursor, Windsurf, VS Code)

Development Commands

# Build the TypeScript project
npm run build

# Run the CLI (after build)
npm start
node dist/cli/index.js <command>

# Development mode (with hot reload)
npm run dev              # CLI
npm run dev:tui          # TUI

# Type checking
npm run typecheck

# Linting
npm run lint             # Check for issues
npm run lint:fix         # Auto-fix issues

# Testing
npm test                 # Run all tests
npm run test:watch       # Watch mode
npm run test:coverage    # With coverage report

# Formatting
npm run format           # Format code
npm run format:check     # Check formatting

# Clean build
npm run clean

Architecture (TypeScript v2.0)

Directory Structure

src/
├── types/              # TypeScript type definitions
│   ├── server.types.ts
│   ├── config.types.ts
│   ├── client.types.ts
│   ├── profile.types.ts
│   ├── settings.types.ts
│   ├── tool.types.ts
│   ├── auth.types.ts
│   ├── daemon.types.ts
│   ├── import-export.types.ts
│   ├── common.types.ts
│   └── index.ts        # Re-exports all types
├── services/           # Business logic services
│   ├── config.service.ts
│   ├── settings.service.ts
│   ├── profile.service.ts
│   ├── client.service.ts
│   ├── testing.service.ts
│   └── index.ts        # Re-exports all services
├── shared/             # Shared utilities
│   ├── colors.ts       # ANSI color codes
│   ├── logger.ts       # Logging utilities
│   ├── prompts.ts      # Interactive prompts
│   └── index.ts
├── cli/                # CLI implementation (commander.js)
│   ├── index.ts        # Main CLI entry point
│   └── commands/       # Command modules
│       ├── server.cmd.ts
│       ├── client.cmd.ts
│       ├── profile.cmd.ts
│       ├── settings.cmd.ts
│       ├── tools.cmd.ts
│       └── utility.cmd.ts
├── tui/                # TUI implementation
│   └── index.ts        # Main TUI entry point
└── index.ts            # Main exports

Read the full file on GitHub · 343 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. 9d ago First seen · 343 lines · 2,903 tokens per session scan B ac7327021bc9

Subscribe to this mod's changes

mcp-server-manager CLAUDE.md is an instructions file published in the GitHub repository sardine-ai/mcp-server-manager (8 stars, last pushed 3d ago), licensed MIT. It adds 2,903 tokens to every session, about $0.0145 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 94% identical to mcp-server-manager AGENTS.md, differing in 16 lines, and is treated as a copy.

Related

Other instructions, from other repositories

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens