"Building a complete Arabic Scratch 3 adventure game" matching MCP servers:

Enables retrieval of compact APG pattern cards, such as button, modal, and dialog, through an MCP tool so clients can consult accessibility guidance.

Bridges AI assistants to running game instances for testing, debugging, and verification. Works with any game engine via a simple TCP protocol.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

MCP server for running deterministic Godot game scenarios, listing available scenarios, running single or soak tests, and reading test reports.

Enables AI agents to create, run, and debug 2D games in a sandboxed engine, providing tools for simulation, state inspection, and quality validation.

Exports Figma designs as ready-to-use HTML/CSS and validates pixel-perfect accuracy with image comparison and visual regression testing.

Enables AI clients to validate game level progression data, audit localization packs for missing translations and dynamic-token mismatches, and run deterministic evaluations of generated puzzle or notification content.

An MCP server connecting Claude AI with game engine runtimes (Unity & Godot) for automated testing, log filtering, and scene hierarchy inspection.

Enables AI-powered interaction with ZenTao 11.3 legacy systems, supporting task, bug, requirement, and test case management via MCP protocol.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Provides deterministic, offline, sourced resolutions for 44 mobile game development problems spanning performance, memory, rendering, store policies, IAP billing, crash vitals, live-ops emergencies, and store-policy deadlines, along with pre-launch checklists and launch-day runbooks. It also statically audits project directories for Google Play and App Store compliance, including target SDK, 16 KB ELF alignment, privacy manifests, and secret-file exposure, without any network calls or shell execution.

MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.

Enables learning and integration testing of the Model Context Protocol by evolving from a minimal server toward production-grade tools, resources, prompts, and agent interoperability.

Generates a pytest suite from acceptance criteria withheld from the coding agent, so the tests can disagree with the code; qikly_run never returns the criteria. The CLI also scores an existing suite by planting faults, and ships as an agent Skill (qikly --install-skill). Runs locally (uvx --from "qikly[mcp]" qikly-mcp): your code and API key stay on your machine.

Zero-dependency MCP server and CLI that proxies, inspects, and analyzes JSON-RPC message streams between MCP clients and servers.

Enables local authoring and testing of Minecraft Java adventure maps through validated MCP tools, including structure building, snapshot/restore, and automated QA.

A shared, concurrency-safe ledger for LLM code audits. It enables multiple agents to collaboratively report, verify, and resolve bugs with deduplication and hallucination resistance.

Autonomous AppSec & DAST code and website security scanner across 12 security domains (260+ controls) with 3-Layer Triage.

An MCP server that gives coding agents hands and eyes on an Android device, providing 19 tools for building, testing, installing, UI inspection, input, logs, and toolchain diagnosis. It returns concise, structured results to make the build-debug loop efficient.

An MCP server that enables AI assistants to discover and execute Nox sessions for project automation tasks like testing, linting, and building. It provides tools to list available sessions and run them using specific Python versions, tags, or keyword expressions.

Makes coding agents better at Godot 4 with 22 MCP tools: an offline Godot 4.7 API reference, a project map, a scored AAA review of GDScript that catches Godot 3 code and invented APIs, safe edits to scenes, settings and names, headless checks, unit tests, play-tests with input and screenshots, plus 3D models built, viewed and checked from code.

Enables AI agents to start, control, and verify local open.mp/SA-MP game servers via MCP stdio, using a headless RakClient to send allowed slash commands and assert round-trip responses.

Enables building and running custom LLM benchmarks with multi-judge evaluation, supporting GUI, MCP client, and CLI usage for ranked, auditable results.

Enables MCP clients to score retrieval quality with recall, precision, nDCG, hit rate and MRR, compare 2-3 configurations with seeded paired-bootstrap confidence intervals, audit agent tool calls against expected traces, and detect prompt regressions against golden sets. It also generates Markdown, JSON or JUnit reports with pass/fail gates, all deterministically and offline without paid API keys.

Connects AI assistants to the live Godot 4 editor so they can build scenes, scripts, resources and animations, run the game, simulate input, capture screenshots and playtest scenarios, and diagnose runtime errors. Every edit flows through undoable changesets that can be diffed, approved, checkpointed or discarded.

Drives a running tModLoader instance from an agent, allowing it to launch the game, issue commands, take screenshots, and read game state as structured data.

An MCP server that lets an AI client enumerate and toggle the in-game menu of an Angel overlay for automated testing.

Godot 4 MCP server with: Test running (GUT/GdUnit4) with structured pass/fail results API docs search with 30+ Godot 3→4 migration mappings Script analysis detecting 10 common GDScript pitfalls Scene/resource file parsing with antipattern detection Viewport screenshot capture LSP diagnostics from Godot's language server TypeScript, cross-platform (macOS/Windows/Linux), published on npm

An independent review layer for AI-generated text: a 10-lens gate run by a separate model over output it did not write, returning the flagged line and the reason for each check rather than a single opaque verdict. A check that cannot complete reports unknown instead of a pass; lens_health needs no API key.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.