AST MCP Server
An MCP (Model Context Protocol) server that provides code structure and semantic analysis capabilities through Abstract Syntax Trees (AST) and Abstract Semantic Graphs (ASG).
Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
An MCP (Model Context Protocol) server that provides code structure and semantic analysis capabilities through Abstract Syntax Trees (AST) and Abstract Semantic Graphs (ASG).
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
git clone https://github.com/angrysky56/ast-mcp-server.git
cd ast-mcp-server
# Install the project in development mode with all dependencies
uv sync
# Or install with specific optional dependencies
uv sync --extra dev # Development tools
uv sync --extra testing # Testing dependencies
uv sync --extra docs # Documentation tools
uv run build-parsers
# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -e .
# Build parsers
python build_parsers.py
Location of config file:
~/Library/Application Support/claude-desktop/claude_desktop_config.json~/.config/claude-desktop/claude_desktop_config.json%APPDATA%\claude-desktop\claude_desktop_config.json{
"mcpServers": {
"AstAnalyzer": {
"command": "uv",
"args": [
"--directory",
"/home/ty/Repositories/ai_workspace/ast-mcp-server/ast_mcp_server",
"run",
"server.py"
]
}
}
}
Important: Replace /absolute/path/to/ast-mcp-server with the actual absolute path on your system.
Restart Claude Desktop to load the new MCP server.
In Claude Desktop, you can now use the AST-based code analysis tools by referencing code files or pasting code snippets.

# Install with development dependencies
uv sync --extra dev
# Install pre-commit hooks (optional)
uv run pre-commit install
To run the server in development mode with the MCP inspector:
# Using uv
uv run --extra dev -- -m mcp dev server.py
# Or using the development script
./dev_server.sh
# Run all tests
uv run --extra testing pytest
# Run tests with coverage
uv run --extra testing pytest --cov=ast_mcp_server --cov-report=html
# Run specific tests
uv run --extra testing pytest tests/test_specific.py
# Format code
uv run black .
uv run isort .
# Lint code
uv run flake8 .
# Type checking
uv run mypy ast_mcp_server/
The server provides the following tools for code analysis:
parse_to_ast: Parse code into an Abstract Syntax Treegenerate_asg: Generate an Abstract Semantic Graph from codeanalyze_code: Analyze code structure and complexitysupported_languages: Get the list of supported programming languagesparse_and_cache: Parse code into an AST and cache it for resource accessgenerate_and_cache_asg: Generate an ASG and cache it for resource accessanalyze_and_cache: Analyze code and cache the results for resource accessparse_to_ast_incremental: Parse code with incremental support for faster processinggenerate_enhanced_asg: Generate an enhanced ASG with better scope handlingdiff_ast: Find differences between two versions of codefind_node_at_position: Locate a specific node at a given line and columnparse_and_cache_incremental: Parse code incrementally and cache the resultsgenerate_and_cache_enhanced_asg: Generate an enhanced ASG and cache itast_diff_and_cache: Generate an AST diff and cache itTo add support for additional programming languages:
uv add tree-sitter-<language>
Update the LANGUAGE_MODULES dictionary in build_parsers.py and ast_mcp_server/tools.py.
Build the parsers:
uv run build-parsers
tree-sitter-python)tree-sitter-javascript)tree-sitter-typescript)tree-sitter-go)tree-sitter-rust)tree-sitter-c)tree-sitter-cpp)tree-sitter-java)The AST MCP Server connects with Claude Desktop through the Model Context Protocol (MCP):
uv run with the appropriate working directoryfilename paths if the provided code is a placeholder.All tool execution happens locally on your machine, with results returned to Claude for interpretation and assistance.
pyproject.toml: Project metadata, dependencies, and tool configurationclaude_desktop_config.json: Example Claude Desktop configurationdev_server.sh: Development server script.gitignore: Git ignore rulesast-mcp-server/
├── ast_mcp_server/ # Main package
│ ├── __init__.py
│ ├── tools.py # Core AST/ASG tools
│ ├── enhanced_tools.py # Enhanced analysis features
│ ├── resources.py # MCP resource handlers
│ └── parsers/ # Tree-sitter parser cache
├── examples/ # Usage examples
├── tests/ # Test suite
├── server.py # Main server entry point
├── build_parsers.py # Parser setup script
├── pyproject.toml # Project configuration
└── README.md # This file
If you encounter parser-related errors:
# Rebuild parsers
uv run build-parsers
# Check for missing language packages
uv add tree-sitter-python tree-sitter-javascript
git checkout -b feature-nameuv run pytestMIT License - see LICENSE file for details.
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "
Übersicht
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Ast läuft lokal über stdio.
Zuletzt geprüft: 2026-11-11. By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.