{"id":"ascii766164696d-log-mcp","name":"log-mcp","af_score":51.2,"security_score":40.5,"reliability_score":13.8,"what_it_does":"log-mcp is a Python-based MCP server that analyzes large log files for AI agents. It provides tools to scan log overviews, search by regex/level/time, extract segments, deduplicate and summarize errors, compute log statistics, compare patterns across files, and classify lines using an optional Rust TF-IDF classifier plus an optional BERT-mini re-scoring stage. It can run with or without the Rust classifier (Python fallback).","best_when":"You have large (tens of MB to many GB) logs where you want an AI agent to narrow down interesting lines/patterns before sending summaries back into a context window.","avoid_when":"You need a standards-based web API with documented HTTP error codes, strict auth/scope semantics, or guaranteed consistent ordering/results; or you must run in environments without permission to execute local commands/models (it appears to run locally via MCP server).","last_evaluated":"2026-03-30T13:48:54.260314+00:00","has_mcp":true,"has_api":false,"auth_methods":["Local execution via MCP CLI integration (no described user auth)."],"has_free_tier":false,"known_gotchas":["No explicit tool I/O schema, argument validation rules, or MCP error taxonomy is provided in the README content; agents may need to handle unexpected tool failures themselves.","Optional ML stages (Rust TF-IDF, optional BERT-mini with GPU/Metal) may cause variability in runtime/latency and failure modes depending on environment.","Classifier can be used where explicit ERROR/FATAL is missing, so agents should not assume level-based results are complete.","Large-file processing may be slow depending on hardware and classifier availability; agent timeouts/retries are not documented."],"error_quality":0.0}