mcp-ast-explorer
Provides deterministic Python codebase symbol exploration using AST parsing, with tools for definition lookup, signatures, references, call chains, and class hierarchy queries.
README
mcp-ast-explorer
<!-- mcp-name: io.github.LovRanRan/mcp-ast-explorer -->
MCP server for deterministic Python codebase symbol exploration.
mcp-ast-explorer indexes Python source files with LibCST and exposes focused MCP tools for codebase onboarding: definition lookup, function signatures, local references, direct call chains, and simple class hierarchy queries.
Codebase Onboarding Stack
mcp-ast-explorer is the semantic symbol layer in a three-server MCP tool stack for Project 6 wayfinder, a codebase onboarding agent.
mcp-repo-mappermaps repository structure, languages, entry points, framework evidence, and Python dependency edges.mcp-ast-explorerprovides symbol-grounded Python definition, signature, reference, call-chain, and class-hierarchy lookups.mcp-test-runnerruns local pytest/Jest checks and coverage summaries so agent claims can be verified against execution.
In wayfinder, this server feeds entry-point and symbol explanation while refusing to invent missing symbols.
Status
This is a Python-only v1. TypeScript is registered as an unsupported backend placeholder so the server has an explicit extension point, but TypeScript analysis is not implemented yet.
The server does not use an LLM for symbol lookup. If a requested symbol or class is not present in the parsed index, tools return a structured not-found result instead of inventing an answer.
Tools
| Tool | Purpose |
|---|---|
health() |
Returns ok for smoke checks. |
find_definition(path, symbol, language="python") |
Finds a module, class, function, or method definition. |
function_signature(path, symbol, language="python") |
Returns the signature for a function or method symbol. |
find_references(path, symbol, language="python") |
Returns same-module CST name references for an existing symbol. |
call_chain(path, from_symbol, depth=2, language="python") |
Returns direct callers detected from local references. |
class_hierarchy(path, class_name, language="python") |
Returns direct subclasses detected from simple base-class names. |
Supported Scope
- Python files parsed by LibCST.
- Symbol kinds: modules, classes, functions, and methods.
- Same-module reference lookup for simple names.
- Direct caller detection from function or method containers.
- Direct subclass detection for simple
class Child(Base):inheritance. - Structured error responses for unsupported languages and missing symbols.
Current Limitations
- Cross-file imports and package-wide resolution are out of scope for v1.
- Aliases, star imports, dynamic attribute access, and qualified references are not resolved.
call_chaincurrently returns direct callers only; recursive multi-hop expansion is not implemented.class_hierarchycurrently returns direct subclasses only and handles simple base names.- TypeScript is intentionally unsupported in v1.
Local Development
Install dependencies:
uv sync --extra dev
Run the MCP server:
uv run mcp-ast-explorer
Run verification:
uv run ruff check .
uv run mypy
uv run pytest
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.