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
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.