#readability

x402-native clean reader. URL in → markdown out. $0.002/call, no signup.

AI agent readability scanner — score any public URL against the Vercel Agent Readability Spec, llmstxt.org, and 6 agent-protocol manifests (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance. Same engine as agent-ready.dev.

Blackmount NLP brings classical text analysis to any MCP client. 45 tools covering tokenization, stemming, readability scores (Flesch, Gunning Fog, Coleman-Liau, ARI, SMOG), VADER-style sentiment, TF-IDF and RAKE keyword extraction, text similarity, cleaning, summarization, and language detection across 18 languages. Zero heavy dependencies — no NLTK, spaCy, transformers, numpy, or scikit-learn. Everything is implemented from scratch in pure Python (stdlib + regex only). The entire wheel is 42KB and installs in under a second. Ideal for agents that need fast, deterministic text analysis without pulling 500MB of ML models. MIT licensed.

MCP server that extracts web content using Readability.js

Mirror of