Dyslexia Steps MCP server

• Registry namecom.dyslexiasteps/dyslexia-stepsverified in the MCP registry

The registry name sits under dyslexiasteps.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-27
• Tools6
• Server calls itselfdyslexiasteps
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 243 ms.

• Its tools do none of the product's use cases we checked: screen a child's reading skills with six short games; practise the weakest reading skill for ten minutes daily; track progress and set daily time limits in a parent area.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• What an agent can do with it0 of 3 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer619 ms
• Space in an agent's context≈ 1,007 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsA · 94 of 100
• Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 2 of 6

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_word_lists

  Lists the available word lists with id, title, language, section, grade range, the source of the grade placement and word count. Filter by language, grade (English lists whose grade range includes it) or section. A grade is a typical…

• get_word_list

  The full list: every word, its groups (for example -at, -an, -ap families), the grade range, the placement basis, the page URL and the license. Use an id from list_word_lists, e.g. short-a, kindergarten, sh.

• get_words_for_grade

  Every different English word from the lists that cover a grade, deduplicated, with the lists each word comes from. Optional section filter (for example only sight words or only cvc). A grade is a typical guide, not a rule: programs and…

• find_words

  Finds words in the lists that start with, end with or contain a letter pattern, for example 'sh', 'ck', '-ight' or 'ai'. Returns each match with its list, grade range and page. Case-insensitive.

• get_placement_basis

  Explains the source of each grade placement: Dolch's own grade levels (1936, public domain), the Common Core Foundational Skills item that names the skill, or a typical sequence when no standard names it. Includes the limits.

• get_citation

  License (CC BY 4.0 for the compilation; the Dolch words are public domain), the citation text and the CSV and JSON download addresses.