A
licenseNot graded
qualityC
maintenanceEnables AI assistants to score English text readability with Flesch, Flesch-Kincaid, Gunning Fog, SMOG, and text statistics, without storing the submitted text.
MIT
PlainGrade
Server Details
English readability scores (Flesch, Flesch-Kincaid, Fog, SMOG) and text stats. Text never stored.
Ownership verified
- Status
- Healthy
- Uptime
- 100.0% over 19 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
A4.1/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of selecting the wrong one. Its purpose (readability scoring) is stated clearly and unambiguously.
Naming Consistency5/5
The single name 'score_readability' follows a clear verb_noun snake_case convention. No competing conventions exist to create inconsistency.
Tool Count3/5
The server wraps a single-purpose scoring engine (POST /v1/score), so one tool is defensible, but the surface is thin with no batch, file, or multi-document option. This is borderline rather than well-scoped.
Completeness3/5
The tool covers all the standard readability formulas, statistics, and long-sentence extraction for one text, which is solid for the core operation. However, there is no batch/multi-text scoring, no comparison, and no configuration beyond a threshold, leaving notable gaps.
Available Tools
1 toolscore_readabilityScore English text readability (Flesch, Flesch-Kincaid, Gunning Fog, SMOG, Coleman-Liau, ARI)ARead-onlyIdempotentInspect
Compute readability scores for English text: Flesch Reading Ease, Flesch-Kincaid grade, Gunning Fog, SMOG, Coleman-Liau, ARI and a consensus grade, with plain-English interpretation, text statistics (words, sentences, syllables, reading and speaking time) and the sentences longer than a threshold. Read-only; the text is scored in memory and never stored or logged. Same engine as the PlainGrade JSON API (POST /v1/score).
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language code. Only English is supported: "en", "en-US", "en-GB", … | en |
| text | Yes | English text to score, up to 20,480 bytes (UTF-8). | |
| include_raw | No | Also return the full /v1/score JSON (every long sentence, unclipped) in structuredContent.raw. Larger output. | |
| long_sentence_words | No | A sentence with more words than this is listed as long (default 25). |
Output Schema
| Name | Required | Description |
|---|---|---|
| raw | No | Full /v1/score response (only when include_raw is true) |
| lang | Yes | |
| tier | No | |
| notes | No | |
| stats | Yes | Counts and averages (words, sentences, syllables, reading_time_seconds, …) |
| engine | No | |
| scores | Yes | |
| version | Yes | |
| text_bytes | No | |
| interpretation | Yes | |
| long_sentences | Yes |
TDQS
A4.2/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety baseline is covered. The description adds genuinely new context beyond the annotations: scoring happens in memory and text is never stored or logged, plus a note that include_raw produces larger output. That is useful privacy and cost context for a read-only tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that puts the deliverables first and the privacy/engine notes last. It is dense and long, but nearly every clause earns its place; only the API-equivalence clause is borderline filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description need not spell out return values, yet it still summarizes them accurately (metrics, consensus grade, statistics, long sentences). Combined with the in-memory/no-logging note and API equivalence, an agent has everything needed to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds downstream meaning the schema does not: it explains that long sentences above a threshold are surfaced, that raw results are unclipped, and that reading/speaking time and text statistics are included. This connects include_raw and long_sentence_words to observable output effects.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Names a specific verb (compute) and resource (readability scores for English text) and enumerates the exact metrics returned, so an agent knows precisely what this produces. It also identifies the underlying engine (PlainGrade JSON API POST /v1/score), which is useful disambiguation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (score English text in memory) and notes the equivalence to the PlainGrade /v1/score endpoint, but gives no explicit when-to-use/when-not guidance and there are no siblings to differentiate against. Adequate but minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
score_readability1 field changed- changed
Output schema / properties / tier / enumPrevious value: -[ - "anonymous", - "free_key" -]New value: +[ + "anonymous", + "free_key", + "pro" +]
1 tool update
- First observed
score_readability
Related MCP Connectors
Text statistics & readability MCP.
Sentiment, language detection, readability, keywords, summaries and profanity filtering
Text tools: stats, language, case, lines, replace, extract, keywords, summary, sentiment, diff.
Scores text for substance, depth, and clarity in under 25ms.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides text statistics and readability scores (Flesch Reading Ease, Flesch-Kincaid Grade Level) via offline, keyless tools.191 npmMIT
- AlicenseNot gradedqualityBmaintenanceProvides text analysis tools including word counting, reading time estimation, keyword density analysis, and sentiment scoring.5 npm37 PyPIMIT
- AlicenseAqualityBmaintenanceMCP server that calculates readability metrics for text, web pages, and PDFs, providing scores like Flesch Reading Ease and grade levels.12Apache 2.0
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.