# PlaySudoku

> Deterministic Sudoku puzzles, progress checks, logical hints, and step-by-step solutions.

- name: io.github.vincentping/playsudoku
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 73/100 flags: no-repository
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.vincentping%2Fplaysudoku
- tools: https://api.protogrid.dev/v1/servers/io.github.vincentping%2Fplaysudoku/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "playsudoku": {
      "type": "http",
      "url": "https://mcp.playsudoku.us/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 35
- drivers: +reachable +uptime-97% ~updated-56d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_sudoku_puzzle (destructiveHint, idempotentHint, openWorldHint); solve_sudoku (destructiveHint, idempotentHint, openWorldHint); explain_next_step (destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,332 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,332 tokens to load them all
- tool set hash: 616fb2d04e3ca92c3a092b826a2b8973
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.vincentping/playsudoku.svg)](https://protogrid.dev/servers/io.github.vincentping/playsudoku)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.playsudoku.us/mcp (streamable-http, auth none, reachable true, uptime30d 0.9741379)

## Packages

_none_

## Tools (4)

- `check_progress`: Check a user's current progress against the correct solution.
Returns factual information only: whether the puzzle is complete, whether all filled cells are correct,
which cells are incorrect (with the entered digit), and how many cells remain empty.
Does not give hints or coaching — use explain_next_step for that.
Use this when the user asks "am I done?" or "did I make any mistakes?"
Every response includes a solve_url where the same puzzle can be continued in the interactive solver.
- `explain_next_step`: Get the next logical solving step for a sudoku puzzle, optionally from a partially-filled state.

TWO-BOARD MODE (puzzle + progress) — use when you know both the original clue grid and the user's current work:
  puzzle: the original 81-char clue string (the given digits only, 0/. for empty cells).
  progress: the user's current 81-char board — must keep all original clue digits in place.
  This mode detects incorrect entries: if any user-filled cell contradicts the solution, the tool returns
  incorrect_cells instead of a step hint, so the user can correct errors before continuing.
  Use this when the user is solving a puzzle they received from get_sudoku_puzzle (puzzle is known).

SINGLE-BOARD MODE (puzzle only, no progress) — use when the original clue grid is unknown (e.g. photo OCR):
  Pass the user's current full board as puzzle with no progress argument.
  The tool treats the board as both the clue grid and the current state, so it will not perform error checking
  (it cannot distinguish given digits from user entries). It simply returns the next logical step.
  Use this when you cannot separate the original clues from the user's entries.

Returns: { technique, explanation, action, tutorial_links } on success, or { incorrect_cells, message } if errors found.
Use this for step-by-step coaching — one hint at a time.
Every response includes a solve_url for continuing the same board interactively and, on success, tutorial_links for the named technique.
- `get_sudoku_puzzle`: Get a random sudoku puzzle from the PlaySudoku.us collection.
Puzzle is returned as an 81-character string: digits 1–9 for given cells, 0 for empty cells.
The response includes the techniques required to solve the puzzle and a solve_url to the interactive solver.
Difficulties: easy (30–38 givens), medium (44–50), hard (50–55), expert (56–62), evil (56–62).
Optional: pass a technique name (e.g. "X-Wing", "Hidden Pair") to get a puzzle that specifically requires that technique — useful when the user wants to practice a particular solving method.
If no puzzle at the requested difficulty uses that technique, the error message lists which difficulties do have it.
Use solve_sudoku for a full step-by-step solution, or explain_next_step to get one hint at a time.
Every response includes a solve_url where the same puzzle can be continued in the interactive solver.
- `solve_sudoku`: Solve a sudoku puzzle completely with step-by-step logical deduction.
Input: 81-character string of digits (0 or . for empty cells). Whitespace is tolerated.
Returns: every solving step with technique name + human-readable explanation + action,
         the final solution string, a technique summary (counts), and tutorial links.
Only uses logical techniques — never guesses. If the puzzle cannot be solved logically,
the steps will end before completion.
Use this when the user wants to understand how to solve a puzzle from scratch.
The response includes a solve_url for continuing the same board interactively and tutorial_links for techniques used in the solution.