What is mcp-chat-human CLAUDE.md?

A CLAUDE.md instruction document for the mcp-chat-human project. It explains the project, its commands, its structure, and how its MCP server works; MCP is a standard way for an AI agent to use external tools.

Installing dependencies, building, testing types, linting, developing, and understanding the server files and message-sending tool.

It gives Claude Code the project-specific context needed to work on the repository consistently.

How palon7/mcp-chat-human configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to palon7/mcp-chat-human. 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/palon7/mcp-chat-human/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/palon7/mcp-chat-human

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/palon7/mcp-chat-human/claude-md/github.svg)](https://agentmods.dev/instructions/palon7/mcp-chat-human/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/palon7/mcp-chat-human/claude-md"><img src="https://agentmods.dev/badge/instructions/palon7/mcp-chat-human/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/palon7/mcp-chat-human/claude-md"><img src="https://agentmods.dev/badge/instructions/palon7/mcp-chat-human/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 449 This file is loaded in full into every session.

When invoked 449 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.

Model	Per session	Once invoked
Fable 5.1	$0.00449	$0.00449
Opus 5	$0.00225	$0.00225
Sonnet 5	$0.00090	$0.00090
Haiku 4.5	$0.00045	$0.00045

Measured 8d ago against content hash 32e4c965725e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-chat-human 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 · 48 lines

What it actually says

CLAUDE.md

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

Project Overview

mcp-chat-help is a Model Context Protocol (MCP) server that enables AI agents to send messages to human users via chat and optionally request responses. It uses stdio transport for communication. For example, we envision using it for scenarios like: "Sending a message to users to ask for help when encountering an unsolvable problem during coding" or "Consulting users to make critical decisions."

Commands

pnpm install      # Install dependencies
pnpm build        # Build (compiles TypeScript to build/ directory)
pnpm clean        # Remove build artifacts
pnpm watch        # Development with hot reload
pnpm dev          # Run with MCP Inspector for debugging
pnpm typecheck    # Type check without building
pnpm lint         # Run ESLint
pnpm lint:fix     # Run ESLint with auto-fix

Architecture

src/index.ts - Entry point; initializes the MCP server with stdio transport
src/server.ts - Server factory; registers the send_message tool
src/config.ts - Environment configuration with Zod validation
src/schema.ts - Zod schemas for tool input/output validation
src/providers/ - Chat provider implementations
- types.ts - ChatProvider interface and types
- errors.ts - Custom error classes
- index.ts - Provider factory
- discord/ - Discord provider implementation

Use the discord.js library for Discord integration.

Docs

Environment Variables

DISCORD_API_KEY (required) - Discord bot token
DISCORD_CHANNEL_ID (required) - Discord channel ID for messages
CHAT_TIMEOUT_MS (optional, default: 600000) - Response timeout in milliseconds
NODE_ENV (optional, default: development) - Environment mode

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.

8d ago First seen · 48 lines · 449 tokens per session scan A 32e4c965725e

Subscribe to this mod's changes

mcp-chat-human CLAUDE.md is an instructions file published in the GitHub repository palon7/mcp-chat-human (0 stars, last pushed 9mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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 2026-09-01.

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

mcp-chat-human: Instructions file for Claude Code