Score text readability (Flesch, SMOG, ARI, grade level) via mcp-readability (npx)

Recipe: Score text readability via mcp-readability

Surface: mcp-readability v1.0.0 (npm) Transport: stdio (NDJSON) Launch: npx -y mcp-readability Tools: 1 — analyze_readability

What it does

Computes four readability scores for any text:

• Flesch Reading Ease (0–100, higher = easier)
• Flesch-Kincaid Grade Level (US grade level)
• SMOG Index (years of education needed)
• Automated Readability Index (grade level)

Also returns: word/sentence/syllable counts, avg words per sentence, avg syllables per word, a reading-level label, target audience, and optional improvement suggestions (long sentences, complex words, passive voice).

Tool schema

{
  "name": "analyze_readability",
  "inputSchema": {
    "type": "object",
    "properties": {
      "text": { "type": "string", "description": "The text to analyze. Any length; minimum ~2 sentences for reliable scores." },
      "include_suggestions": { "type": "boolean", "description": "When true (default), returns improvement suggestions." }
    },
    "required": ["text"]
  }
}

Verified execution trace

Request:

{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"analyze_readability","arguments":{"text":"The quick brown fox jumps over the lazy dog. This is a simple sentence that most people can understand without any difficulty at all. Machine learning models process natural language using transformer architectures with multi-head self-attention mechanisms and feed-forward neural network layers."}}}

Response (5ms):

{
  "scores": {
    "flesch_reading_ease": 33.5,
    "flesch_kincaid_grade": 12.1,
    "smog_index": 12.5,
    "ari": 13.5
  },
  "reading_level": "High School (9th–12th grade)",
  "audience": "High school students",
  "stats": {
    "word_count": 42,
    "sentence_count": 3,
    "syllable_count": 79,
    "avg_words_per_sentence": 14,
    "avg_syllables_per_word": 1.88
  },
  "summary": "Flesch Reading Ease: 33.5 | FK Grade: 12.1 | SMOG: 12.5 | ARI: 13.5 — High School (9th–12th grade) (42 words, 3 sentences)",
  "suggestions": [
    "1 word has 5+ syllables — consider simpler alternatives: architectures"
  ]
}

Performance

• Cold start: ~200ms (npx install adds ~5s on first run)
• Tool call latency: ~5ms (pure in-process, no network)
• No dependencies beyond Node.js

When to use

• Pre-publish content quality gate (blog posts, docs, marketing copy)
• Agent-driven content optimization loops
• Comparing readability before/after edits
• Ensuring documentation matches target audience grade level