phonsteps
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
phonsteps
Which word lists exist, which words belong to a grade, and which words match a letter pattern? phonsteps is a local forwarding client for the hosted dyslexiasteps MCP service: it answers tools/list locally from the captured tool definitions and forwards every call to the service, returning the answers exactly as the service sends them back.
The catalogue is a published set of structured phonics word lists (a CC BY 4.0 compilation; the Dolch words are public domain). Lists are browsable by language, grade, and section; words can be pulled per grade or found by pattern; and the service also explains how each grade placement was assigned and how to cite and reuse the lists. There is no write, signup, or send tool in this surface.
The tools
list_word_lists— Lists the available word lists with id, title, language, section, grade range, placement source, and word count. Optional filters:language(en,de,es,fr,nl,pt-br),grade(English lists covering it), andsection(cvc,families,sight,digraphs,patterns,wordlist). No required parameters.get_word_list— The full list: every word, its groups (for example the -at, -an, -ap families), grade range, placement basis, page URL, and license. Requiresid(for exampleshort-a,kindergarten,sh).get_words_for_grade— Every different English word from the lists covering a grade, deduplicated, with the lists each word comes from. Requiresgrade(pre-k,kindergarten,grade-1,grade-2,grade-3); optionalsectionfilter andlimit(1–1500, default 300).find_words— Words that start with, end with, or contain a letter pattern (for examplesh,ck,-ight,ai), case-insensitive, each match returned with its list, grade range, and page. Optionalcontains,starts_with,ends_with,language,grade, andlimit(1–500, default 60). No required parameters.get_placement_basis— How grades were assigned: Dolch's own grade levels, the Common Core Foundational Skills item naming the skill, or a typical sequence when no standard names it, including the limits. No parameters.get_citation— The license, the citation text, and the CSV and JSON download addresses for the word lists. No parameters.
A grade here is a typical guide, not a rule: programs and standards differ, and it is not an assessment of any child. English lists are placed by grade; lists in other languages follow each language's own curriculum and have no grade.
Related MCP server: @cyanheads/datamuse-mcp-server
Install and run
As an MCP server via npm:
npx -y @reneturcios/phonsteps mcpMCP client configuration:
{
"mcpServers": {
"phonsteps": {
"command": "npx",
"args": ["-y", "@reneturcios/phonsteps", "mcp"]
}
}
}As a container:
docker run -i ghcr.io/cloudcorprecords/phonsteps
docker run --rm ghcr.io/cloudcorprecords/phonsteps find_words '{}'CLI
One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:
phonsteps list_word_lists '{"language":"en","section":"cvc"}'
phonsteps get_word_list '{"id":"short-a"}'
phonsteps get_words_for_grade '{"grade":"grade-1","limit":50}'
phonsteps find_words '{"contains":"ight"}'
phonsteps get_placement_basis '{}'
phonsteps get_citation '{}'
phonsteps --versionExit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.
Configuration
DYSLEXIASTEPS_MCP_URL— Overrides the upstream endpoint. The default is the pinned hosted endpoint,https://mcp.dyslexiasteps.com/mcp. (The override variable is a reconstruction added by this rebuild.)
The upstream registry record declares no headers, so no authentication header is ever sent; the tool surface was captured keyless.
Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with phonsteps error:.
How forwarding works
The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any isError flag and any extra fields the service includes.
Development
npm install
npm run build # tsc -> dist/ (dist/cli.js is the bin)
npm test # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev # run the CLI from sourceThe test suite checks the served tool list against the captured surface (all 6 tools, deep-equal, in order, titles included exactly as captured, and no required key added to the four tools that carry none), exercises the session handshake and its reuse, verifies that no Authorization or X-API-Key header is ever sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.
License
MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Phonics word lists and reading-game catalogue for dyslexia support. Read-only.
AI-assisted English lexical records. Stored-only batch lookup; coverage and quality vary.
Public read-only MCP access to digital learning concepts, semantic relationships, and citations.
Authoritative JLPT-graded Japanese dataset (kanji, vocab, grammar, history) via MCP and REST.
Related MCP Servers
AlicenseAqualityCmaintenanceEnables MCP clients to query sourced phonics and sight word lists by grade, language, section, or spelling pattern, and to retrieve full lists, placement rationale, citations, and CSV/JSON downloads.635 npmMIT- AlicenseNot gradedqualityBmaintenanceEnables finding rhymes, synonyms, antonyms, sound-alikes, and spelling matches, and exploring word associations through the Datamuse API. Supports combining meaning, sound, spelling, and lexical-relation constraints for writing, editing, puzzles, and naming.88 npm2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables users to look up, search, decode, compare, and explore contemporary internet English, texting shorthand, regional expressions, and clearly labeled non-graphic adult vocabulary through a remote, zero-auth Streamable HTTP endpoint.MIT

opencidian-mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables looking up Chinese and Vietnamese dictionary data — hanzi, pinyin, Hán Việt readings, character breakdowns, words containing a character, meaning search, and full text annotation — and suggesting corrections via a public issue. It is a read-only, no sign-in endpoint for the OpenCidian dataset.MIT