GDScript Code Analyzer
Enables AI assistants to analyze GDScript code structure, extract symbols, functions, and dependencies without reading entire files. Supports efficient navigation and understanding of Godot game engine codebases through tree-sitter parsing.
README
mcp-gdscript
A Model Context Protocol (MCP) server for GDScript code analysis. This server allows AI assistants to understand GDScript code structure without reading entire files, making it efficient for large codebases.
Features
- File Structure Analysis: Extract classes, functions, signals, variables, and enums from GDScript files
- Symbol Search: Find specific symbols and get their location and type
- Dependency Extraction: Identify extends, preload, and import statements
- Direct Code Analysis: Analyze GDScript code snippets without file I/O
- Tree-Sitter Powered: Accurate parsing using the official GDScript tree-sitter grammar
Installation & Usage
With uvx (Recommended)
The simplest way to use this server - no installation required:
{
"mcpServers": {
"gdscript": {
"command": "uvx",
"args": ["mcp-gdscript"]
}
}
}
With npm/npx
{
"mcpServers": {
"gdscript": {
"command": "npx",
"args": ["mcp-gdscript"]
}
}
}
Local Installation
# Clone the repository
git clone https://github.com/yourusername/mcp-gdscript
cd mcp-gdscript
# Install in development mode
pip install -e .
# Run the server
mcp-gdscript
Available Tools
1. analyze_gdscript_file
Analyze a GDScript file and extract its complete structure.
Input:
file_path(string): Path to the .gd or .gdscript file
Output: Returns JSON with:
symbols: Lists of classes, functions, signals, variables, and enums with line numberssummary: Total counts for each symbol type
Example:
{
"file": "scenes/player.gd",
"symbols": {
"classes": [],
"functions": [
{"name": "_ready", "line": 5, "column": 0},
{"name": "_process", "line": 10, "column": 0}
],
"signals": [
{"name": "health_changed", "line": 2, "column": 0}
],
"variables": [],
"enums": []
},
"summary": {
"total_classes": 0,
"total_functions": 2,
"total_signals": 1,
"total_variables": 0,
"total_enums": 0
}
}
2. get_gdscript_structure
Get a human-readable structure view of a GDScript file.
Input:
file_path(string): Path to the .gd or .gdscript file
Output: A formatted text representation showing the file structure with line numbers.
Example output:
=== GDScript File Structure ===
Signals:
- health_changed (line 2)
Functions:
- _ready (line 5)
- _process (line 10)
3. find_gdscript_symbol
Search for a specific symbol in a file.
Input:
file_path(string): Path to the .gd or .gdscript filesymbol_name(string): Name of the symbol to find
Output: Symbol information including type, name, and location.
Example:
{
"type": "function",
"name": "_ready",
"line": 5,
"column": 0
}
4. get_gdscript_dependencies
Extract all dependencies from a GDScript file.
Input:
file_path(string): Path to the .gd or .gdscript file
Output: Lists of extends, preload, and import statements.
Example:
{
"file": "scenes/enemy.gd",
"dependencies": {
"extends": ["Character"],
"preload": ["res://scenes/explosion.tscn"],
"import": []
}
}
5. analyze_gdscript_code
Analyze GDScript code provided directly as a string.
Input:
code(string): GDScript source code
Output: Complete analysis including structure, symbols, and summary.
Use Cases
- Codebase Navigation: Quickly understand the structure of large GDScript files
- API Documentation: Generate documentation from code structure
- Dependency Analysis: Understand script relationships and dependencies
- Code Review: Get structure overview before detailed review
- Refactoring Aid: Understand what needs to be updated when refactoring
Configuration
Environment Variables
RUST_LOG: Set logging level (e.g.,debug,info,warn)
Performance Tips
- For large files (>10MB), the server efficiently extracts structure without loading full content into context
- Symbol extraction is optimized for typical GDScript files (< 50MB)
- The tree-sitter parser uses cached grammar for performance
Limitations
- Currently optimized for GDScript 4.x and later
- Complex macro expansions may not be fully analyzed
- Some edge cases in dynamic code patterns may not be captured
Development
Setup
pip install -e ".[dev]"
Testing
pytest
Code Style
black .
ruff check .
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
License
MIT License - see LICENSE file for details
References
Troubleshooting
"Module not found" errors
Make sure you're using Python 3.10 or later and have installed the server correctly.
Parse errors for GDScript 3.x
This server is optimized for GDScript 4.x. For GDScript 3.x, some features may not work as expected.
Performance issues
If analyzing very large files, consider:
- Splitting large scripts into smaller modules
- Using the structure tool instead of full analysis
- Analyzing specific symbols instead of entire files
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.