Skills-MCP-Hudu: Instructions file for Claude Code

CLAUDE.md

Skills-MCP-Hudu CLAUDE.md is an instructions file for Claude Code from DevSkillsIT/Skills-MCP-Hudu. It costs 3,944 tokens per session, scanned A, original, MIT.

Instructions for building an MCP server around the Hudu API, a service interface for Hudu documentation and IT records. The server is designed to use HTTP, Docker, environment-based configuration, and current MCP and TypeScript packages.

In plain words
What is it for?
Generating or maintaining a production-ready Hudu integration with health checks, typed errors, warnings, and predictable resource-and-action operations.
Why use it?
It gives an agent clear requirements for connecting to Hudu without hard-coded secrets and for handling missing or partial API access.

Instructions file for Claude Code

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

This is DevSkillsIT/Skills-MCP-Hudu's own configuration. It tells Claude Code how to work on Skills-MCP-Hudu 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 Skills-MCP-Hudu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DevSkillsIT/Skills-MCP-Hudu. 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/DevSkillsIT/Skills-MCP-Hudu/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/DevSkillsIT/Skills-MCP-Hudu

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 Skills-MCP-Hudu CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/devskillsit/skills-mcp-hudu/claude-md"><img src="https://agentmods.dev/badge/instructions/devskillsit/skills-mcp-hudu/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,944 This file is loaded in full into every session.
When invoked 3,944 The same file — it is already loaded in full.
Security scan A 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 $0.03944 $0.03944
Opus 5 $0.01972 $0.01972
Sonnet 5 $0.00789 $0.00789
Haiku 4.5 $0.00394 $0.00394

Measured 9d ago against content hash e6ac44e7c83c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Skills-MCP-Hudu CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **Health check**: `curl http://localhost:3100/health`
CLAUDE.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MCP Hudu Server

You are Claude Code. Generate and maintain a production-ready MCP server that wraps the Hudu API from hudu.json (Swagger/OpenAPI).

Objective

Ship an MVP MCP server that:

  • Conforms to the LATEST MCP specification (always current version - NO legacy versions).
  • ALWAYS uses the LATEST official MCP TypeScript SDK: @modelcontextprotocol/sdk (update immediately when new versions available)
  • EXCLUSIVELY uses Streamable HTTP Transport on port 3100 - NO STDIO, NO SSE, HTTP ONLY.
  • Implements the resource+action pattern (predictable verbs across domains).
  • Runs reliably in Docker, with health/readiness endpoints.
  • Handles partial API access gracefully (typed errors, warnings, next steps).
  • Uses .env for all Hudu config (no secrets in code).
  • MANDATORY: Always update to latest packages - security and compatibility requirement.

Environment & Configuration

Create a .env file from .env.example:

HUDU_BASE_URL=https://your-hudu.example.com
HUDU_API_KEY=your-api-key
HUDU_TIMEOUT=30000
MCP_SERVER_PORT=3100
LOG_LEVEL=info

Fail fast if required vars are missing. No hard-coded secrets.


Connection from Claude Code (HTTP ONLY)

ONLY HTTP transport is supported - no STDIO configuration:

Add MCP server to Claude Code:

claude mcp add --transport http hudu http://127.0.0.1:3100/mcp

Alternative Claude Desktop config:

{
  "mcpServers": {
    "hudu": {
      "transport": "http",
      "url": "http://127.0.0.1:3100/mcp"
    }
  }
}

IMPORTANT: Never configure STDIO transport. This server only supports HTTP.


Deliverables (what you should generate)

  • src/server.ts — MCP HTTP server wiring (Streamable transport), health endpoints:
    • GET /health (liveness)
    • GET / (server info)
    • ALL /mcp (MCP endpoint)
  • src/hudu-client.ts — Hudu API client with typed methods
  • src/tools/* — 55 tools com prefixo hudu_ e padrão manage/search:
    • Core: articles, companies, assets, passwords (manage + search = 8 tools)
    • Procedures: procedures, procedure tasks (manage + search = 4 tools)
    • Folders: kb article folders (manage + search = 2 tools)
    • Networks: networks, VLANs, VLAN zones, IP addresses (manage + search = 8 tools)
    • Storage: uploads, rack storages, rack items, public photos (manage + search = 8 tools)
    • Labels: definições de etiqueta, etiquetas aplicadas (manage + search = 4 tools)
    • Flags: tipos de sinalização, registros sinalizados (manage + search = 4 tools)
    • Utility: admin, search global, navigation (3 tools)
    • Outros: folders, websites, asset layouts, activity logs, expirations, relations, magic dash, bridges de resources/prompts
  • src/types.ts — TypeScript types from OpenAPI
  • hudu.json — OpenAPI/Swagger spec (reference only)
  • Dockerfile — Multi-stage build, non-root runtime
  • .env.example — Environment template
  • docker-compose.existing-traefik.yml — Compose for an existing Traefik
  • package.json — scripts: dev, build, start, lint, type-check

Read the full file on GitHub · 394 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 · 394 lines · 3,944 tokens per session scan A e6ac44e7c83c

Subscribe to this mod's changes

Skills-MCP-Hudu CLAUDE.md is an instructions file published in the GitHub repository DevSkillsIT/Skills-MCP-Hudu (3 stars, last pushed 12d ago), licensed MIT. It adds 3,944 tokens to every session, about $0.0197 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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