# io.github.mauricekleine/nonobench

An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.1.0
- **Author:** io.github.mauricekleine
- **License:** Unknown
- **Endpoints:** streamable-http https://www.nonobench.com/mcp
- **Source:** https://github.com/mauricekleine/nonobench
- **Endpoint health:** reachable (last checked 2026-10-02T15:45:28.452Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 2 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-02T15:45:12.467Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

14 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `get_leaderboard` — Nonobench models ranked by accuracy, overall or for one grid size. Effort defaults to all levels; use effort=best to match the homepage.
- `list_providers` — Provider ids, names, families and variant counts.
- `list_families` — Model families, efforts and best variants.
- `compare_models` — Compare two or more model ids or family names side by side.
- `set_filters` — Update the visible leaderboard filters and URL.
- `get_model_results` — Accuracy, cost and latency for one model, per grid size.
- `list_puzzles` — The benchmark puzzles with ids and row/column clues.
- `get_puzzle_results` — Per-model outcomes for a puzzle, optionally including parsed grids.
- `get_model_puzzles` — Which puzzles a model solved, missed, or did not run.
- `check_solution` — Check a nonogram grid (row-major 0/1 string) against a puzzle's clues.
- `open_puzzle` — Show a puzzle in the puzzle explorer on this page.
- `nonobench`
- `get_puzzle` — One puzzle, including the clue text models were prompted with. The reference solution is only included on request; some puzzles have several valid solutions.
- `list_runs` — Individual benchmark runs (one model on one puzzle), optionally with the raw prompt and model output.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"nonobench\": {\n      \"type\": \"http\",\n      \"url\": \"https://www.nonobench.com/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.mauricekleine%2Fnonobench
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.mauricekleine%2Fnonobench/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.mauricekleine%2Fnonobench
- HTML page: https://forgeregistry.com/registry/io.github.mauricekleine%2Fnonobench
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.