mcp-ts-toolskit: Instructions file for Claude Code

CLAUDE.md

mcp-ts-toolskit CLAUDE.md is an instructions file for Claude Code from thomas92fr/mcp-ts-toolskit. It costs 948 tokens per session, scanned A, original, Apache-2.0.

Project instructions for developing the mcp-ts-toolskit Model Context Protocol (MCP) server, a program that gives AI clients tools for tasks such as file access, web searches, and document conversion.

In plain words
What is it for?
Use it when compiling, bundling, watching, or inspecting the TypeScript server, or when working on its configuration, logging, and tool modules.
Why use it?
It gives contributors the project overview, build commands, file locations, and development conventions in one place.

Instructions file for Claude Code

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

This is thomas92fr/mcp-ts-toolskit's own configuration. It tells Claude Code how to work on mcp-ts-toolskit 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-ts-toolskit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thomas92fr/mcp-ts-toolskit. 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/thomas92fr/mcp-ts-toolskit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thomas92fr/mcp-ts-toolskit

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-ts-toolskit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thomas92fr/mcp-ts-toolskit/claude-md/github.svg)](https://agentmods.dev/instructions/thomas92fr/mcp-ts-toolskit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thomas92fr/mcp-ts-toolskit/claude-md"><img src="https://agentmods.dev/badge/instructions/thomas92fr/mcp-ts-toolskit/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-ts-toolskit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thomas92fr/mcp-ts-toolskit/claude-md"><img src="https://agentmods.dev/badge/instructions/thomas92fr/mcp-ts-toolskit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 948 This file is loaded in full into every session.
When invoked 948 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 $0.00948 $0.00948
Opus 5 $0.00474 $0.00474
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 8d ago against content hash c7337ebcefd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-ts-toolskit 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 8d 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 · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 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

This is @thomas92fr/mcp-ts-toolskit - a comprehensive Model Context Protocol (MCP) server providing secure, configurable tools for file system operations, web searches, document conversion, project management, and generative AI capabilities via PiAPI.ai integration.

Common Commands

Building and Development

  • npm run compile - Compile TypeScript source code and make scripts executable
  • npm run build - Full build process (compile + webpack bundle)
  • npm run watch - Watch mode for development with automatic recompilation
  • npm run inspector - Build and run with MCP inspector for debugging

Key Build Files

  • Main entry point: src/index.ts
  • Compiled output: build/
  • Bundled distribution: dist/bundle.cjs

Architecture Overview

Core Structure

The project follows a modular architecture with tools organized by category:

  • FastMCP Framework: Uses fastmcp as the MCP server foundation
  • Configuration System: JSON-based config with path validation and security
  • Logging: Winston-based logging with daily rotation
  • Tool Categories: FileSystem, Web, Git, Pandoc, NPM, .NET, System, PiAPI

Main Application Flow (src/index.ts)

  1. Loads configuration from MCP_TOOLSKIT_CONFIG_PATH environment variable
  2. Initializes Winston logger with file rotation
  3. Creates FastMCP server instance
  4. Registers all tool categories and their individual tools
  5. Adds resource endpoints for logs and prompts
  6. Starts server on stdio transport

Tool Architecture Pattern

Each tool follows a consistent pattern:

  • Located in src/tools/{category}/{tool_name}.ts
  • Exports an object with Add_Tool(server, config, logger) method
  • Uses Zod schemas for parameter validation
  • Implements security through config.validatePath() and config.validateTool()

Configuration System (src/models/appConfig.ts)

  • IAppConfig Interface: Defines configuration structure
  • Security: Path validation ensures operations stay within AllowedDirectories
  • Tool Control: ForbiddenTools array can disable specific tools
  • API Integration: Separate config sections for BraveSearch and PiAPI
  • Environment Support: Configuration loaded via JSON file path from env var

Read the full file on GitHub · 100 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. 8d ago First seen · 100 lines · 948 tokens per session scan A c7337ebcefd1

Subscribe to this mod's changes

mcp-ts-toolskit CLAUDE.md is an instructions file published in the GitHub repository thomas92fr/mcp-ts-toolskit (0 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 948 tokens to every session, about $0.0047 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

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