Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

PuzzleTide

NPM · PUZZLETIDE-MCP · SCANNED SEP 20

Word search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.

Available components

0 this week 80 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 34 of 103 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2084 tokens (~138/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "eval_check" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the PuzzleTide MCP server?

PuzzleTide runs locally as an npm package, launched with npx -y puzzletide-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · puzzletide-mcp

# add to Claude Code
claude mcp add catorch-puzzletide -- npx -y puzzletide-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "catorch-puzzletide": {
      "command": "npx",
      "args": [
        "-y",
        "puzzletide-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "catorch-puzzletide": {
      "command": "npx",
      "args": [
        "-y",
        "puzzletide-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add catorch-puzzletide -- npx -y puzzletide-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "catorch-puzzletide": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "puzzletide-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add catorch-puzzletide --command npx --arg -y --arg puzzletide-mcp
# ~/.hermes/config.yaml
mcp_servers:
  catorch-puzzletide:
    command: "npx"
    args: ["-y", "puzzletide-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "catorch-puzzletide": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "puzzletide-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add catorch-puzzletide -t stdio -c npx -a -y puzzletide-mcp
// mcp.json
{
  "mcpServers": {
    "catorch-puzzletide": {
      "command": "npx",
      "args": [
        "-y",
        "puzzletide-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 +1
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 9 Sept 26 +1
    • Stability: 0.97 → pass security
  • 8 Sept 26 0
    • Security disclosure: unverified → fail functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/puzzletide-mcp@0.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 103 packages
Packages resolved 103
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~2,000 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
eval_check ~98

Grades a JSON answers file against a tasks file produced by eval generate. Verification is by construction: sudoku answers must satisfy sudoku rules and preserve the givens; word search answers must spell the word along a straight line in the grid. Outputs per-task results and a score summary.

NameTypeReqDescription
answersstring|numberJSON array of {id, answer} (required)
tasksstring|numberTasks JSON from eval generate (required)

No output schema declared.

No examples provided.

eval_generate ~183

Emits a JSON array of puzzle tasks with objectively checkable answers. Types: sudoku (unique-solution puzzles; answers verified against sudoku rules + givens) and wordsearch (answers verified against the grid letters). Deterministic with --seed, so a (seed, type, difficulty, n) tuple names a reproducible benchmark set.

NameTypeReqDescription
difficultystring|numbersudoku: easy|medium|hard|expert; wordsearch: easy|medium|hard (default: medium)
nstring|numberNumber of tasks (default: 10)
outstring|numberWrite tasks JSON to a file instead of stdout
seedstring|numberSeed for a reproducible task set (default: 1)
typestring|numberTask type: sudoku or wordsearch (default: sudoku)

No output schema declared.

No examples provided.

play_daily ~38

Prints a daily sudoku (medium difficulty) that is the same for everyone on the same UTC calendar day. Solve more puzzles at puzzletide.com.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

puzzle_crossword_generate ~332

Builds an interlocking crossword grid with standard numbering. Words come from --words "WORD: clue; WORD2: clue2", --file (JSON [{word,clue}] or "WORD: clue" lines), or --theme (clues are auto-generated puzzle-style hints). Words that cannot interlock are reported as unplaced. Deterministic with --seed. Online version: https://puzzletide.com/crossword

NameTypeReqDescription
countstring|numberNumber of words to use from the theme/file (default: 10)
filestring|numberJSON array of {word, clue} or "WORD: clue" lines
paperstring|numberPDF paper size: letter or a4 (default: letter)
pdfstring|numberAlso write a printable PDF worksheet to <file>
seedstring|numberSeed for reproducible output (number or word)
sizestring|numberWorking grid size before trimming (5-25) (default: 15)
solutionbooleanPrint the solution instead of the puzzle
solutionPagebooleanOmit the solution page from PDF output — set false to disable
svgstring|numberAlso write an SVG image to <file>
themestring|numberUse a bundled word bank theme (auto-generated clues)
titlestring|numberTitle used in SVG/PDF output
wordsstring|numberSemicolon-separated "WORD: clue" pairs

No output schema declared.

No examples provided.

puzzle_sudoku_generate ~223

Generates a 9x9 sudoku at easy/medium/hard/expert difficulty. Every puzzle is verified to have exactly one solution. Deterministic with --seed. The canonical string format is 81 characters, row by row, "." for empty cells. Online version: https://puzzletide.com/sudoku

NameTypeReqDescription
difficultystring|numberOne of: easy, medium, hard, expert (default: medium)
paperstring|numberPDF paper size: letter or a4 (default: letter)
pdfstring|numberAlso write a printable PDF worksheet to <file>
seedstring|numberSeed for reproducible output (number or word)
solutionbooleanPrint the solution instead of the puzzle
solutionPagebooleanOmit the solution page from PDF output — set false to disable
svgstring|numberAlso write an SVG image to <file>
titlestring|numberTitle used in SVG/PDF output

No output schema declared.

No examples provided.

puzzle_sudoku_solve ~119

Solves a 9x9 sudoku via backtracking. Input: 81 characters row by row with 1-9 for givens and 0/./_ for empty cells (whitespace and separators are ignored), passed inline, via --file, or on stdin. Reports whether the solution is unique. Online version: https://puzzletide.com/sudoku

NameTypeReqDescription
filestring|numberRead the grid from a file
gridstring81-character puzzle string (or "-" for stdin)

No output schema declared.

No examples provided.

puzzle_sudoku_validate ~97

Checks a 9x9 sudoku grid for well-formedness, conflicting givens, solvability, and whether the solution is unique (a proper sudoku has exactly one). Same input formats as sudoku solve. Online version: https://puzzletide.com/sudoku

NameTypeReqDescription
filestring|numberRead the grid from a file
gridstring81-character puzzle string (or "-" for stdin)

No output schema declared.

No examples provided.

puzzle_wordsearch_generate ~431

Places every word in a letter grid (8 possible directions, difficulty presets) and fills the rest with random letters. Deterministic with --seed. Words come from --words, --file (one per line), or --theme (bundled PuzzleTide word banks). Output: text grid, --json structured data, --svg image, or --pdf printable worksheet with solution page. Online version: https://puzzletide.com/word-search

NameTypeReqDescription
colsstring|numberGrid columns (overrides --size)
countstring|numberNumber of words to use from the theme/file (default: 12)
difficultystring|numberDirection preset: easy (E,S), medium (+diagonals), hard (all 8) (default: medium)
directionsstring|numberExplicit directions (comma-separated from: N,NE,E,SE,S,SW,W,NW)
filestring|numberRead words from a file (one per line or comma-separated)
paperstring|numberPDF paper size: letter or a4 (default: letter)
pdfstring|numberAlso write a printable PDF worksheet to <file>
rowsstring|numberGrid rows (overrides --size)
seedstring|numberSeed for reproducible output (number or word)
sizestring|numberSquare grid size (6-30); computed from words if omitted
solutionbooleanPrint the solution instead of the puzzle
solutionPagebooleanOmit the solution page from PDF output — set false to disable
svgstring|numberAlso write an SVG image to <file>
themestring|numberUse a bundled word bank theme (see: ptide words themes)
titlestring|numberTitle used in SVG/PDF output
wordsstring|numberComma-separated words, e.g. "cat,dog,fish"

No output schema declared.

No examples provided.

words_anagram ~52

Finds single-word anagrams of the given letters within the bundled word bank sample.

NameTypeReqDescription
lettersstringyesLetters to rearrange
limitstring|numberMaximum results (default: 50)

No output schema declared.

No examples provided.

words_categories ~30

Lists the bundled PuzzleTide word bank categories (animals, geography, holidays, ...) with their theme counts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

words_list ~114

Prints the words of one bundled theme, optionally filtered by length, shuffled by --seed, and limited by --count. Useful as input for generators or other tools.

NameTypeReqDescription
countstring|numberMaximum number of words
maxLengthstring|numberMaximum word length
minLengthstring|numberMinimum word length
seedstring|numberShuffle deterministically before applying --count
themestringyesTheme id, e.g. animals/ocean-animals

No output schema declared.

No examples provided.

words_match ~78

Matches the bundled word bank sample against a pattern where "_" or "?" is any letter, e.g. "c_r_l" matches CORAL. Helpful when stuck on a crossword or word puzzle.

NameTypeReqDescription
limitstring|numberMaximum results (default: 50)
patternstringyesPattern with _ or ? wildcards

No output schema declared.

No examples provided.

words_random ~80

Picks a random word from the bundled word banks — the same pool the hangman game uses. Deterministic with --seed.

NameTypeReqDescription
minLengthstring|numberMinimum word length (default: 4)
seedstring|numberSeed for reproducible output
themestring|numberRestrict to one theme

No output schema declared.

No examples provided.

words_stats ~24

Prints the size of the bundled word bank: categories, themes, unique words.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

words_themes ~101

Lists the bundled starter themes (30 generic word lists; the full curated collection is at puzzletide.com). Filter by --category or full-text --search. Theme ids look like "animals/ocean-animals".

NameTypeReqDescription
categorystring|numberOnly themes in this category
limitstring|numberMaximum results (default: 50)
searchstring|numberFull-text search over id, title, and description

No output schema declared.

No examples provided.

Common questions

What is the PuzzleTide MCP server?

PuzzleTide is an MCP server listed in the public MCP registry as io.github.catorch/puzzletide. Word search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals. This page covers its npm package (puzzletide-mcp).

Is the PuzzleTide MCP server safe to use?

PuzzleTide scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the PuzzleTide MCP server expose?

PuzzleTide exposes 15 tools: eval_check, eval_generate, play_daily, puzzle_crossword_generate, puzzle_sudoku_generate, and 10 more. Their descriptions and schemas cost roughly 2,000 tokens of context every time the server is loaded.

Is the PuzzleTide MCP server still maintained?

PuzzleTide is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the PuzzleTide MCP server under?

PuzzleTide declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.