"Conda-Forge" matching MCP servers:

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.

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

Enables AI coding agents to run Foundry tests and builds and receive compact, structured failure reports with decoded reasons, fuzz counterexamples or invariant call sequences, logs, and short traces. It also distinguishes genuine test failures from cases where tests did not run, returning actionable errors instead of false zero-failure results.

An MCP server that turns Zod schemas into mocks, violations, and contract tests, enabling AI agents to reason about API contracts without manually crafting payloads.

Enables agents and security automation to adjudicate proposed defense mutations against a sealed, canonicalized attack scenario, enforcing reproduction, impact-screening, regression, and proven-improvement gates before promoting at most one candidate. Every verdict, rejected candidate, and rejection reason is sealed into a recomputable SHA-256 Merkle evidence root and hash-linked lineage that can be independently verified without trusting the server.

Enables Python developers to define MCP tools via decorators, auto-generate schemas and tests, and package compliant MCP servers with CLI scaffolding and JSON-RPC 2.0 stdio transport.

An experimental MCP server for MNCS-native development and evidence control, enabling Codex to manage project authority, candidate lineage, evidence gaps, and evaluator-mode boundaries.

Enables visual authoring and testing of MCP tools, resources, and prompts across Bun, Node.js, and Python via standard MCP transports.

Enables MCP clients to build Logisim circuits from natural language by adding pins, gates, LEDs and wires through tools that return exact port coordinates, then saving the result as a .circ file. It also runs Logisim's own loader to read the file back and report dangling wire ends and multi-driver shorts.