What is demomcp CLAUDE.md?

A project instruction file for developing and running the sedwardstx/demomcp Python package. It records installation, formatting, type-checking, linting, testing, and server-start commands.

Use it to install the package, run Black, isort, mypy, and flake8, execute pytest tests with coverage, verify server imports, and start the MCP server.

It gives an agent one place to find the repository's expected development commands and setup details. This reduces uncertainty when installing dependencies or checking changes.

How sedwardstx/demomcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sedwardstx/demomcp. 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/sedwardstx/demomcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sedwardstx/demomcp

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/sedwardstx/demomcp/claude-md/github.svg)](https://agentmods.dev/instructions/sedwardstx/demomcp/claude-md)

Your own site

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

Per session 2,516 This file is loaded in full into every session.

When invoked 2,516 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	$0.02516	$0.02516
Opus 5.5	$0.01006	$0.01006
Sonnet 5.5	$0.00503	$0.00503
Haiku 4.5	$0.00252	$0.00252

Measured 2mo ago against content hash dca240b7cf34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

demomcp 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 · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 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.

Development Commands

Build and Install

# Install the package in development mode
pip install -e .

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

# On Windows, ensure pywin32 is properly installed for Event Log access
# If you encounter issues, try:
pip install pywin32>=300
python -c "import win32api"  # Test Windows API access

Code Quality

# Format code
black .
isort .

# Type checking
mypy src

# Linting
flake8

# Run all quality checks
black . && isort . && mypy src && flake8

Testing

# Run all tests with proper PYTHONPATH
PYTHONPATH=src python3 -m pytest tests/ -v

# Run tests with coverage
PYTHONPATH=src python3 -m pytest --cov=mcp_log_analyzer tests/

# Run specific test file
PYTHONPATH=src python3 -m pytest tests/test_base_parser.py -v

# Test server import
PYTHONPATH=src python3 -c "from mcp_log_analyzer.mcp_server.server import mcp; print('Server import successful')"

Running the MCP Server

Important: MCP servers don't show output when started - they communicate via stdin/stdout with MCP clients.

# Start the MCP server (runs silently)
python main.py

# Test the server is working
python check_server.py

# Add to Claude Code
claude mcp add mcp-log-analyzer python main.py

# List MCP servers
claude mcp list

# Remove MCP server
claude mcp remove mcp-log-analyzer

No Output is Normal: When you run python main.py, you won't see any console output. The server is running and waiting for MCP protocol messages from clients like Claude Code.

Architecture Overview

MCP Server Structure

This project follows the FastMCP framework pattern, refactored from the quick-data-mcp architecture:

Entry Point (main.py): Simple script that imports and runs the MCP server
MCP Server (src/mcp_log_analyzer/mcp_server/server.py): FastMCP server coordinator
Tools (src/mcp_log_analyzer/mcp_server/tools/): Organized MCP tools by category
Resources (src/mcp_log_analyzer/mcp_server/resources/): System monitoring resources
Prompts (src/mcp_log_analyzer/mcp_server/prompts/): Comprehensive user guides
Core Logic (src/mcp_log_analyzer/core/): Models and configuration
Parsers (src/mcp_log_analyzer/parsers/): Log format-specific parsers

Read the full file on GitHub · 273 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.

2mo ago First seen · 273 lines · 2,516 tokens per session scan A dca240b7cf34

Subscribe to this mod's changes

demomcp CLAUDE.md is an instructions file published in the GitHub repository sedwardstx/demomcp (5 stars, last pushed 1y ago), licensed MIT. It adds 2,516 tokens to every session, about $0.0101 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.

demomcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
demomcp CLAUDE.mdsedwardstx/demomcp	Instructions file	5	1y ago	MIT	A	2,516	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

demomcp: Instructions file for Claude Code