AgenticMCP: Instructions file for Claude Code

CLAUDE.md

AgenticMCP CLAUDE.md is an instructions file for Claude Code from mattma87/AgenticMCP. It costs 475 tokens per session, scanned A, original, MIT.

Project instructions for AgenticMCP, a Python MCP server that lets AI assistants use external tools and data through a standard connection. They cover setup, development commands, testing, and the project's file structure.

In plain words
What is it for?
Setting up the Python project, running the MCP server, changing its implementation, and checking changes with pytest, Black, Ruff, and mypy.
Why use it?
They help the coding agent understand how the server is organised and how to run, test, format, lint, and type-check it.

Instructions file for Claude Code

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

This is mattma87/AgenticMCP's own configuration. It tells Claude Code how to work on AgenticMCP 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 AgenticMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mattma87/AgenticMCP. 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/mattma87/AgenticMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mattma87/AgenticMCP

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 AgenticMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mattma87/agenticmcp/claude-md/github.svg)](https://agentmods.dev/instructions/mattma87/agenticmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mattma87/agenticmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mattma87/agenticmcp/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 AgenticMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mattma87/agenticmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mattma87/agenticmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 475 This file is loaded in full into every session.
When invoked 475 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 $0.00475 $0.00475
Opus 5.5 $0.00190 $0.00190
Sonnet 5.5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 2mo ago against content hash 477595b4db43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AgenticMCP 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 2mo 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 · 91 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

AgenticMCP is a Python-based Model Context Protocol (MCP) server. MCP is a protocol that allows AI assistants to interact with external tools and data sources through a standardized interface.

Development Commands

Setup

# Create and activate virtual environment
python -m venv .venv
.venv\Scripts\activate  # Windows
# source .venv/bin/activate  # Linux/Mac

# Install with dev dependencies
pip install -e ".[dev]"

Running the Server

# Run the MCP server via stdio
agenticmcp

# Or run directly with Python
python -m agenticmcp.server

Testing

# Run all tests
pytest

# Run specific test file
pytest tests/test_specific.py

# Run with coverage
pytest --cov=agenticmcp

Code Quality

# Format code
black src/

# Check linting
ruff check src/

# Type checking
mypy src/

Architecture

The project follows a standard Python package structure:

  • src/agenticmcp/ - Main package directory
    • server.py - MCP server implementation with tool registration and handlers
    • __init__.py - Package initialization

The server uses the mcp library to implement the MCP protocol over stdio. Tools are registered using the @server.list_tools() decorator and handled via @server.call_tool().

Adding New Tools

To add a new tool:

  1. Add the tool definition in server.py within the list_tools() function
  2. Implement the tool's logic in the call_tool() function
  3. Follow the MCP tool schema format for input validation

MCP Integration

The server communicates via stdio and can be integrated with MCP clients using:

{
  "mcpServers": {
    "agenticmcp": {
      "command": "uvx",
      "args": ["--from", "agenticmcp", "agenticmcp"]
    }
  }
}
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. 2mo ago First seen · 91 lines · 475 tokens per session scan A 477595b4db43

Subscribe to this mod's changes

AgenticMCP CLAUDE.md is an instructions file published in the GitHub repository mattma87/AgenticMCP (0 stars, last pushed 8mo ago), licensed MIT. It adds 475 tokens to every session, about $0.0019 per session on Opus 5.5. 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

AgenticMCP CLAUDE.md compared with instructions from other repositories

AgenticMCP CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
AgenticMCP CLAUDE.mdmattma87/AgenticMCPInstructions file08mo agoMITA475Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot