PuzzleTide MCP server
io.github.catorch/puzzletide·v0.2.1Word search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.
0 stars38 downloads/wk
Reviews
Write oneNobody has reviewed PuzzleTide yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
PuzzleTide tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 71 days ago12/15
- Maintainer identitynamespace and repository owner differ4/10
How PuzzleTide compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 65% of 4,460 AI and agents servers
- Downloads a week
- 38
- more than 30% of 1,538 AI and agents servers with a package
Install PuzzleTide in Claude Code, Cursor or VS Code
Runs npx -y puzzletide-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add puzzletide -- npx -y puzzletide-mcp
What the publisher says
From the PuzzleTide repository's README, as published. We do not edit it. Read it on GitHub
<!-- Keyword rationale (d4s / DataForSEO, 2026-07-16, google en): word search generator 33,100/mo KD37 · word search maker 33,100 KD40 · sudoku solver 40,500 KD41 sudoku generator 1,000 KD9 · sudoku puzzle generator 170 KD10 · crossword generator 12,100 KD51 printable word search 18,100 KD5 · printable sudoku puzzles 4,400 KD15 · expert sudoku 2,400 KD0 daily sudoku 27,100 KD37 · hangman game 40,500 KD35 · llm evals 480 KD28 Dev modifiers (cli/npm/javascript/github variants) are all ≤10/mo — the surfaces that matter are GitHub search, npm search, and Google snippets of the repo page, all of which read the repo description, package.json description/keywords, and README H1/H2s. Contiguous phrases to keep intact: "word search generator", "crossword generator", "sudoku generator", "sudoku solver", "printable word search", "printable sudoku", "expert sudoku", "daily sudoku", "LLM evals", "puzzle generator CLI", "MCP server". Top-page deep links (GSC 2026-07, by clicks): mystery-and-murder printable word search (237), /hangman (25), /printable (10), dyslexic-friendly blog post (9), /maker (4). Banned claims (not shipped): word search solver, crossword solver, anagram solver (word tools search only the 30 starter banks), MCP server, PNG output, AI clue generation, nonograms/cryptograms, speed guarantees for expert sudoku, "full English dictionary". IP rule: the package ships only the 30 generic starter themes in scripts/wordbanks-source.json — NEVER include or reference-compile the proprietary puzzletide.com word bank dataset here. -->
PuzzleTide CLI — word search, crossword & sudoku generator
Word search generator, crossword generator, and sudoku generator + solver in one local-first puzzle generator CLI — with printable PDF worksheets, starter word banks, verifiable LLM evals, and bundled agent skills. From the makers of puzzletide.com.
Install
npm install -g puzzletide
ptide --versionThe package installs both binaries:
- ptide
- puzzletide
Why generate puzzles with a CLI
Ask a language model to write a word search and you get a grid where half the words are broken; ask it for a sudoku and you usually get one with several solutions, or none. Grids are exactly the kind of output LLMs are bad at and deterministic code is good at.
PuzzleTide CLI is that deterministic code:
part of the output, and the generators are property-tested.
- Every word search word is placed and verifiable — placement coordinates are
- Every generated sudoku is checked to have exactly one solution.
- Every crossword is validated against its own clues before it's returned.
- Same --seed in, same puzzle out, on any machine.
The package also ships SKILL.md agent skills, so coding agents (Pi, Hermes, OpenClaw, and other SKILL.md-based systems) reach for the CLI instead of hand-writing grids.
Command model
ptide <namespace> <operation> [input] [options] # for humans
ptide run <tool-id> [input] [options] --json # canonical, for scripts/agents
ptide tools list | search <q> | info <id> | docs <id>
ptide agent manifestUse short commands interactively and canonical tool ids in automation:
ptide sudoku generate --difficulty hard
ptide run puzzle.sudoku.generate --difficulty hard --jsonWord search generator
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
PuzzleTide: common questions
- Is PuzzleTide MCP server safe?
- Mostly: it is graded B (82/100). Read the PuzzleTide safety report
- How do I install PuzzleTide?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does PuzzleTide need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is PuzzleTide maintained?
- The last commit was 110 days ago (2026-07-17). The latest release is v0.2.1.
- What can I use instead of PuzzleTide?
- Servers from other publishers that do the same job: OpenWorkProof MCP server, PDF MCP server and three.ws Provenance MCP server.
- How does PuzzleTide compare with other AI and agents MCP servers?
- safety score 82/100 (higher than 65% of 4,460 AI and agents servers); downloads a week 38 (more than 30% of 1,538 AI and agents servers with a package). Full comparison.
Alternatives to PuzzleTide
Same job from other publishers: the closest match first, then the best rated.
- OpenWorkProofVerifiable agent evidence; opt-in Codex guard and reference SOC alert review.not reviewedEstablishedA
- PDFAgentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.not reviewedEstablishedA
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB
- AuscaPay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.not reviewedEstablishedA