godot-correctness-mcp
Offline static correctness MCP server for Godot 4.x GDScript projects that lints code, looks up API symbols, and validates scenes/resources, all without a running editor.
README
godot-correctness-mcp
Offline static correctness MCP server for Godot 4.x GDScript projects
A Model Context Protocol server (and gdcorrect CLI) that statically checks the
correctness of Godot 4.x GDScript projects. It runs headless, offline, and in
CI — it never launches the editor, never needs a running Godot instance, and
never touches the network at runtime.
Three pillars
- GDScript linting — anti-pattern detection via a committed tree-sitter
grammar (WASM). Rules like
delta-misuse,get-node-in-process,missing-onready,untyped-declaration,await-misuse,stringly-nodepath,connect-without-disconnect,float-grid-equality. See docs/lint.md. - Cross-version API lookup & diff — query classes/methods/properties/signals and diff the API between Godot 4.4 and 4.5, from committed offline symbol databases. See docs/symbol-db.md.
- Scene / resource / registry analysis — validate
.tscn,.tres, andproject.godot, including deep validation of data-driven.tresregistries (the dangling-path check). See docs/scenes.md.
Non-goals
- No live bridge. It does not connect to a running editor or game.
- No editor plugin. Nothing to install inside Godot.
- No C#. GDScript only.
- Nothing older than Godot 4.4. Symbol data is pinned to 4.4 and 4.5.
This is deliberately the complement to the live-session Godot MCP tools: it is the one you run in CI and headless pipelines.
Installation
As an MCP server (Claude Desktop / Cursor mcpServers config):
{
"mcpServers": {
"godot-correctness": {
"command": "npx",
"args": ["-y", "@tmhs/godot-correctness-mcp"]
}
}
}
As a CLI:
npx -y @tmhs/godot-correctness-mcp gdcorrect lint . --format json
MCP surface
Tools: server_info; api_symbol_lookup, api_class_summary, api_diff;
lint_file, lint_project; validate_scenes, validate_project_config,
validate_registries, project_report.
Resources: curated GDScript skill snippets under skill:// (data-driven
resources, signal hygiene, typed GDScript, preload vs load).
CLI and CI
gdcorrect <command> <projectPath> [--format json|pretty], where <command> is
lint, validate-scenes, validate-project, validate-registries, or report.
JSON is the primary, machine-readable format. Exit codes: 0 clean, 1 on
any error-severity finding, 2 on tool failure.
# .github/workflows/godot-correctness.yml
jobs:
correctness:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with: { node-version: 22 }
- name: Lint GDScript (fails on error-severity findings)
run: npx -y @tmhs/godot-correctness-mcp gdcorrect lint . --format json
- name: Validate registries
run: npx -y @tmhs/godot-correctness-mcp gdcorrect validate-registries . --format json
Configuration
Place godot-correctness.config.json at your project root (see
godot-correctness.config.example.json):
enable/disable rules, override severities, set include/exclude globs, and declare
registryDirs / pathPropertyPatterns for registry validation. Full reference in
docs/lint.md and docs/scenes.md.
Symbol database regeneration
The API pillar reads committed gzipped symbol DBs generated locally from pinned Godot binaries (CI validates them but never runs Godot). Regeneration procedure: docs/symbol-db.md.
Roadmap
See ROADMAP.md and BACKLOG.md.
Contributing
See CONTRIBUTING.md for guidelines.
License
CC-BY-NC-ND-4.0 -- see LICENSE for details.
Built by TMHSDigital
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.