AST MCP Server
@angrysky56
AST MCP Server について
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
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ast-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is AST MCP Server?
AST MCP Server is an MCP (Model Context Protocol) server that provides code structure and semantic analysis capabilities through Abstract Syntax Trees (AST) and Abstract Semantic Graphs (ASG). It supports multiple programming languages (Python, JavaScript, TypeScript, Go, Rust, C/C++, Java) and is compatible with Claude Desktop and other MCP clients.
How to use AST MCP Server?
Requires Python 3.9+ and either uv (recommended) or pip. Clone the repository, run uv sync then uv run build-parsers. Configure Claude Desktop by editing its configuration file and adding an MCP server entry with the absolute path to the server directory. Claude can then use tools like parse_to_ast, generate_asg, analyze_code, etc. to analyze code snippets or local files.
Key features of AST MCP Server
- Parse code into Abstract Syntax Trees (AST)
- Generate Abstract Semantic Graphs (ASG) from code
- Analyze code structure and complexity
- Support for multiple programming languages
- Incremental parsing for large files
- AST diffing to identify code changes
- Resource caching for improved performance
Use cases of AST MCP Server
- Analyze code structure in any supported language using Claude Desktop
- Compare code versions using AST diffing
- Cache analysis results for repeated queries
- Use incremental parsing for large files
- Locate specific nodes in code by line and column
FAQ from AST MCP Server
What languages does AST MCP Server support?
Python, JavaScript, TypeScript, Go, Rust, C, C++, and Java.
Where does data live?
All tool execution happens locally on your machine, with results returned to Claude for interpretation.
How do I configure Claude Desktop?
Edit the Claude Desktop configuration file (located at ~/Library/Application Support/claude-desktop/claude_desktop_config.json on macOS, with similar paths on Linux and Windows) and add the AST MCP server entry with the absolute path to the server directory.
What are the prerequisites?
Python 3.9 or higher and the uv package manager (recommended) or pip.
How do I add support for a new language?
Install the corresponding tree-sitter language package, update the LANGUAGE_MODULES dictionary in build_parsers.py and ast_mcp_server/tools.py, then run uv run build-parsers.
「その他」の他のコンテンツ
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Awesome Mlops
visengerA curated list of references for MLOps
コメント