Overview
Word Lexicon Analyzer works on the letters of a single `word`. Before any check, all whitespace is removed and the word is lowercased, so "Race Car" is analyzed as `racecar`. Most flags are computed from the characters of that normalized string; `hasAnagram` and `isScrabbleValid` also look the word up in a bundled English word list of about 95,000 lowercase entries (the Hunspell en-US list, including plurals and verb forms).
`sortedForm` is the characters sorted in code-point order, and `isAlphagram` is true when the word already equals its sorted form, as in "almost". `isPalindrome` compares the string with its reverse. `canBePalindromeAnagram` counts each character and is true when at most one character appears an odd number of times, meaning the letters could be rearranged into a palindrome. `isIsogram` is true when no character repeats.
`hasAnagram` is true when another word in the list uses exactly the same letters, so "listen" returns true (silent, enlist, tinsel) and "quixotic" returns false. The input itself does not need to be a word. `isPangramCandidate` is true only when the string has 26 or more distinct characters, which a single English word almost never does. `isScrabbleValid` is true when the word is at least two letters, uses only a to z, and is in the word list, so a nonsense string fails. Capitalized entries such as place and personal names are excluded, as Scrabble excludes proper nouns. The list is a general English dictionary rather than an official tournament list, so some Scrabble-only words such as "qi" and "za" return false.
Digits, hyphens and apostrophes are kept as characters and take part in every check, so strip them first if you only want letters compared. The response is identical on every plan.
Live Test Word Analyzer Skill Skill →
The tool
Once your client is connected to the VerveKit server, this appears in its tool list as WordAnalyzerSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.
{
"name": "WordAnalyzerSkill",
"arguments": {
"word": "listen"
}
}You do not name the tool yourself; the model picks it. Asking about listen in the terms this skill covers is enough for it to reach for WordAnalyzerSkill on its own — naming it explicitly also works, and is the way to force the call.
Connecting
One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.
{
"mcpServers": {
"vervekit": {
"url": "https://api.vervekit.com/v1/mcp"
}
}
}https://api.vervekit.com/v1/mcpPer-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.
| Argument | Type | Description |
|---|---|---|
wordRequired | string | The word to analyze |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"word": "listen",
"isAlphagram": false,
"sortedForm": "eilnst",
"isPalindrome": false,
"hasAnagram": false,
"isIsogram": true,
"isPangramCandidate": false,
"isScrabbleValid": true,
"canBePalindromeAnagram": false
}
}
Response fields
Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.
| Field | Type | Example | Description |
|---|---|---|---|
word | string | listen | The analyzed word |
isAlphagram | boolean | false | Whether the word's letters are already in alphabetical order |
sortedForm | string | eilnst | The word's letters sorted alphabetically, used to match anagrams |
isPalindrome | boolean | false | Whether the word is a palindrome |
hasAnagram | boolean | false | Whether another English word uses exactly the same letters |
isIsogram | boolean | true | Whether the word repeats no letter |
isPangramCandidate | boolean | false | Whether the word contributes rare letters useful in a pangram |
isScrabbleValid | boolean | true | Whether the word is in the bundled English word list (letters a-z only, no proper nouns) |
canBePalindromeAnagram | boolean | false | Whether the letters can be rearranged into a palindrome |
Failure modes
Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.
| Status | What it means |
|---|---|
400 / 422 | The arguments did not validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Blocked by a key restriction or an IP allow-list. Never a bad identity. |
404 | This skill is not part of VerveKit. Check the catalog. |
429 | Out of credits, or a brief rate limit. The message tells them apart. |
A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Word Game Validation
- Puzzle game backends verify player submissions against Scrabble eligibility and immediately flag valid palindromes for bonus scoring.
- Anagram Puzzle Generation
- Crossword and puzzle constructors use sorted letter forms to group matching anagrams and test word rearrangements for hidden riddles.
- Vocabulary Drill Generation
- Language learning platforms detect isograms and alphagrams to build spelling exercises focused on words with non-repeating letters.
- Pangram Challenge Construction
- To build daily pangram challenges, editorial teams filter candidate lists to find terms that supply rare and uncommon letters.
Other ways to use Word Analyzer Skill
Set up Word Analyzer Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.
Related
More in Text Processing: