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
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。