Readingspeed

What Readingspeed is for

"How many words per minute did I just read?", "is 250 wpm fast for studying a textbook?", "what reading level is this paragraph?", "quiz me on this passage I just read" — a fully local reading-speed and comprehension self-test toolkit. Nothing is looked up: every number and every question is computed directly from the passage and timing you supply.

What it does

wpm_calculator computes real words-per-minute from a passage and how many seconds it took to read it, and can compare that figure against a documented benchmark range for a reading purpose — skimming, leisure reading, or studying. reading_benchmarks returns those benchmark ranges on their own, with the research they come from. readability_score gives a Flesch-Kincaid grade level and Flesch reading ease for any text. comprehension_check mechanically generates fill-in-the-blank and true/false questions derived directly from the sentences of your own passage — a real content word blanked out of an actual sentence, or a sentence quoted verbatim (true) versus lightly altered by negation, an antonym swap, or a changed number (false). reading_test runs all three at once for a single combined self-test.

What is computed vs. documented

The words-per-minute math, the readability formula, and every comprehension question are computed directly from your input, live, with no bundled dataset behind them. Only the benchmark ranges in reading_benchmarks are documented reference figures — drawn from reading-speed research, notably Brysbaert (2019)'s meta-analysis of adult silent-reading rates (~238 wpm nonfiction, ~260 wpm fiction) and the skimming/studying ranges widely used in study-skills pedagogy — not something this connector measured itself.

Not a duplicate of Brightwise

Brightwise's reading_level tool applies the same Flesch-Kincaid formulas for a kids' audience. Readingspeed reimplements that formula (the lineage is documented in its source) for general/adult use and adds what Brightwise doesn't have: real WPM measurement against documented benchmarks, and a comprehension-question generator derived from the caller's own text.

What it is not

This is a self-assessment tool, not a diagnostic or clinical instrument. Reading speed and comprehension vary enormously with text difficulty, prior familiarity, and the individual reader — the benchmark ranges are typical figures from published research, not fixed thresholds a normal reader must hit, and the generated comprehension questions are mechanically derived, not independently verified against outside facts.

Built and maintained by Unify Dynamics LLC. Contact: agent@connectorbay.com.

Readingspeed — Privacy Policy

Effective 28 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What Readingspeed is. Readingspeed is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for reading-speed and comprehension self-testing: words-per-minute calculation, benchmark comparison, readability scoring, and comprehension-question generation. You interact with your assistant; the assistant sends us only the values needed for that one response.

What we receive. The arguments of each tool call — a passage of text and how many seconds it took to read it, a reading purpose to benchmark against, or text to score for readability or generate comprehension questions from — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.

Everything is computed on our server and nothing is stored. Words-per-minute, readability scores, and comprehension questions are all computed or generated directly from the text and numbers you send in that one request; the reading-speed benchmark ranges are a small fixed reference table bundled with the server. No request is forwarded to any third party, and no passage or query text is logged in request bodies, recorded, or used to train anything.

What we do not receive or store. We do not receive your conversation with the assistant or any identifying information about you, and we do not build a reading profile from your queries — each call is answered independently and no passage you submit is retained after the response is sent.

Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.

Sub-processors. None — every tool is computed locally. Hosting: Vercel (United States regions).

Legal bases and your rights. For users in California, the EU/UK and elsewhere, our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.

Children. Readingspeed is a general-audience reading-skills tool operated through the adult or organization running the AI assistant; it is not directed at children, and no tool requests a child's name or other identifying details.

Changes. We will post changes here with a new effective date.

Readingspeed — Terms of Service

Effective 28 September 2026. These terms govern use of the Readingspeed connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

1. The Service. Readingspeed computes words-per-minute reading speed, compares it against documented benchmark ranges, scores text readability, and generates comprehension questions derived from caller-supplied text. It is accessed through an AI assistant or directly over MCP or HTTP.
2. Self-assessment content, not a diagnostic tool. Readingspeed's calculations and generated questions are general self-assessment aids, not a clinical or diagnostic measure of reading ability, and not a substitute for a reading specialist, educator, or learning-disability evaluation.
3. Benchmark ranges are typical, not universal. The reading-speed benchmark ranges reflect commonly documented research and study-skills guidance; individual reading speed and comprehension vary with text difficulty, familiarity, and the reader, and falling outside a range is not evidence of any impairment.
4. Mechanically generated questions. Comprehension questions are generated automatically from the text you submit and are not independently fact-checked, edited, or reviewed by a person before being returned.
5. Acceptable use. Automated use within the published rate limits is welcome.
6. Availability. The Service is provided "as is" without warranty. We may change, limit or discontinue it at any time.
7. Data. Our Privacy Policy describes what we process. In short: your input is answered on our server and nothing is stored.
8. Pro keys. Optional Pro API keys are issued at our discretion, are personal to the holder and may be revoked for abuse.
9. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss arising from use of or reliance on the Service. Our total liability is limited to US $100.
10. Governing law. California law; venue in San Mateo County, California.
11. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/readingspeed

Readingspeed support

Email agent@connectorbay.com. We answer within two business days.

• MCP endpoint: https://readingspeed.connectorbay.com/mcp
• REST API: https://readingspeed.connectorbay.com/openapi.json
• Live status: https://readingspeed.connectorbay.com/health

When you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Readingspeed never asks for them.