ast-outline-mcp
Enables AI coding agents to efficiently explore codebases by providing structural outlines, module digests, symbol bodies, and AST-aware grep via MCP.
README
ast-outline-mcp
An MCP (Model Context Protocol) server for ast-outline — a tree-sitter-based CLI that lets AI coding agents pull exactly what they need from a codebase: structural outlines, module digests, symbol bodies, and AST-aware grep.
Why
LLM coding agents explore codebases by reading files directly. A 1200-line file costs 1200 lines of context just to answer "what methods are in here?" — ast-outline provides the file's shape in 60–100 lines, and this MCP server exposes that functionality to any MCP-compatible client.
Prerequisites
- Node.js >= 18
ast-outlineCLI installed and available on PATH (installation guide)
uv tool install ast-outline
Installation
Run via npx (no install needed)
npx ast-outline-mcp
Install globally
npm install -g ast-outline-mcp
ast-outline-mcp
MCP Client Configuration
Add to your MCP client config (e.g., Claude Desktop):
{
"mcpServers": {
"ast-outline": {
"command": "npx",
"args": ["ast-outline-mcp"]
}
}
}
Local development
npm install
npm run build
npm start
Tools
outline
Get a structural outline of one or more files or directories. Returns signatures with line ranges (no bodies).
Parameters:
paths(string[], required) — File or directory paths to outlinejson(boolean) — Return machine-readable JSON outputimports(boolean) — Include import/use/using statementsnoPrivate(boolean) — Exclude private membersnoFields(boolean) — Exclude fields/propertiesnoDocs(boolean) — Exclude documentation commentsnoAttrs(boolean) — Exclude attributes/decorators
digest
Get a compact one-page module map of a directory. Each file gets a size label and token estimate.
Parameters:
paths(string[], required) — Directory paths to digestjson(boolean) — Return machine-readable JSON output
show
Extract the full source body of one or more symbols from a file.
Parameters:
file(string, required) — File path to extract symbols fromsymbols(string[], required) — Symbol names to extractjson(boolean) — Return machine-readable JSON outputsignature(boolean) — Return header/signature only, no body
grep
AST-aware structural search across files. Matches grouped by enclosing class/function.
Parameters:
pattern(string, required) — Search pattern (literal or regex, auto-detected)paths(string[], required) — File or directory paths to searchjson(boolean) — Return machine-readable JSON outputkind(enum: def|call|ref|import) — Narrow results by classification kindwordMatch(boolean) — Match whole words onlycaseInsensitive(boolean) — Case-insensitive matchingfilesOnly(boolean) — List matching files onlycount(boolean) — Show match counts per filemaxCount(number) — Maximum number of matches per file
Prompts
explore_codebase
A prompt that guides an LLM to efficiently explore a codebase using ast-outline tools.
Development
npm install
npm test
npm run build
Supported Languages
ast-outline supports 20+ languages including TypeScript, Python, Go, Rust, C#, Java, Kotlin, Ruby, PHP, and more. See the full list.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。