What is log-mcp CLAUDE.md?

Project instructions for log-mcp, an MCP server that helps an AI analyze log files without loading all of them into its context.

Use them to build, test, run, and extend log analysis for JSON and text logs, including searching, statistics, comparisons, and error analysis.

They explain the project structure, setup commands, parser behavior, tests, and known improvement areas before code changes are made.

How ascii766164696D/log-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ascii766164696D/log-mcp. 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/ascii766164696D/log-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ascii766164696D/log-mcp

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/ascii766164696d/log-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ascii766164696d/log-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ascii766164696d/log-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ascii766164696d/log-mcp/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/ascii766164696d/log-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ascii766164696d/log-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,187 This file is loaded in full into every session.

When invoked 1,187 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	$0.01187	$0.01187
Opus 5.5	$0.00475	$0.00475
Sonnet 5.5	$0.00237	$0.00237
Haiku 4.5	$0.00119	$0.00119

Measured 2mo ago against content hash 174855e2645a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

log-mcp 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 · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project overview

log-mcp is an MCP server that gives LLMs tools for analyzing log files without loading them into context. It auto-detects log formats, normalizes variable parts for pattern matching, and provides overview/search/compare/error-analysis tools.

Build & test

uv run pytest           # run all tests
uv run pytest -v        # verbose
uv run log-mcp          # start the MCP server (stdio transport)

No build step — uv run handles everything via pyproject.toml.

Architecture

src/log_mcp/
  parsing/          # Format detection + parsers (JSON, text, adaptive)
  tools/            # One module per MCP tool (overview, search, segment, stats, errors, compare)
  normalize.py      # Pattern normalization (UUIDs, hex, IPs, numbers → placeholders)
  server.py         # FastMCP server setup, registers all tools
  util.py           # Shared helpers (file validation, time parsing)

Detection order: JSON → TextLogParser (hardcoded patterns) → AdaptiveTextParser (timestamp anchor discovery) → fallback.

What could be improved

These are genuine gaps I noticed while building and testing against real log files — not speculative wishlist items.

Parser gaps

Zookeeper/Log4j embedded levels. Lines like 2017-... - INFO [main:ZooKeeper@...] - Session established have the level buried inside the line after a - separator. The text parser doesn't recognize this; all entries get level=None. The adaptive parser could learn this pattern but currently doesn't look for - LEVEL [ anchors.
TextLogParser pattern locking is fragile. It locks to the first regex that matches and uses it for the entire file. If a file has a preamble (config dump, banner) before the actual log lines start, it may lock to the wrong pattern and miss everything else.
No logfmt support. key=value key2=value2 structured logs (common in Go services) aren't recognized. Would need a dedicated parser.
No XML/HTML log support. Log4j XML appender output, Windows Event Log exports — these exist in the wild but aren't handled.

Read the full file on GitHub · 79 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 · 79 lines · 1,187 tokens per session scan A 174855e2645a

Subscribe to this mod's changes

log-mcp CLAUDE.md is an instructions file published in the GitHub repository ascii766164696D/log-mcp (101 stars, last pushed 8mo ago), licensed MIT. It adds 1,187 tokens to every session, about $0.0047 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 2026-08-30.

Building agents

log-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
log-mcp CLAUDE.mdascii766164696D/log-mcp	Instructions file	101	8mo ago	MIT	A	1,187	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

log-mcp: Instructions file for Claude Code