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

Recipe: Score text readability via mcp-readability (npx)

Surface

• Package: mcp-readability (npm)
• Launch: npx -y mcp-readability (stdio)
• Auth: none — pure in-process computation, no external API calls
• Tools: analyze_readability (1 tool)

What it does

Takes any text (minimum ~2 sentences) and returns:

• 4 readability scores: Flesch Reading Ease, Flesch-Kincaid Grade Level, SMOG Index, Automated Readability Index (ARI)
• Reading level: Elementary → Middle School → High School → College → Graduate
• Target audience: e.g. "College students / professionals"
• Text stats: word count, sentence count, syllable count, avg words/sentence, avg syllables/word
• Improvement suggestions (optional, on by default): flags long sentences (>25 words), complex words (5+ syllables), passive voice instances

Parameters

When to use

• Before publishing blog posts, docs, or marketing copy — verify it matches the target audience's reading level
• Evaluating legal/technical text for plain-language compliance
• SEO content optimization (Google favors readable content)
• Comparing draft revisions for readability improvement

Verified trace (2026-06-13)

Input text: "The quick brown fox jumps over the lazy dog. This is a simple sentence that most people can read easily. However, some texts contain multisyllabic terminology and convoluted syntactical structures that significantly impede comprehension for the average reader, particularly when the subject matter pertains to specialized or technical domains requiring prerequisite knowledge."

Result:

{
  "scores": {
    "flesch_reading_ease": 15.2,
    "flesch_kincaid_grade": 15.5,
    "smog_index": 15.2,
    "ari": 16.2
  },
  "reading_level": "College (13th–16th grade)",
  "audience": "College students / professionals",
  "stats": {
    "word_count": 52,
    "sentence_count": 3,
    "syllable_count": 107,
    "avg_words_per_sentence": 17.3,
    "avg_syllables_per_word": 2.06
  },
  "summary": "Flesch Reading Ease: 15.2 | FK Grade: 15.5 | SMOG: 15.2 | ARI: 16.2 — College (13th–16th grade) (52 words, 3 sentences)",
  "suggestions": [
    "1 sentence exceeds 25 words — consider splitting. Example: \"However, some texts contain multisyllabic terminology and convoluted syntactical…\"",
    "4 words have 5+ syllables — consider simpler alternatives: multisyllabic, terminology, significantly, particularly"
  ]
}

MCP handshake

→ initialize (protocolVersion: "2024-11-05")
← serverInfo: { name: "mcp-readability", version: "1.0.0" }
→ tools/list
← 1 tool: analyze_readability
→ tools/call analyze_readability { text: "..." }
← scores + reading_level + audience + stats + suggestions

Cold start ~3s (npx download), subsequent calls sub-second. Pure computation — no network calls after launch.