// MCP TOOL REFERENCE

AST TOOLS

13 tools from the Ast MCP Server, categorised by risk level.

View the Ast policy → Token cost: 909 tokens →

// ALL 13 AST TOOLS

READ 11 tools

Read check_symbol_grounding Assess a symbol's AI grounding quality (docs, type clarity, depth). Read codebase_audit Alias for hygiene_audit. Read find_implementations Find implementations of interfaces or abstract classes. Read find_references Find all usages of a symbol across the project. Read get_call_hierarchy Find callers and callees for a symbol. Read get_file_structure Get structural overview of a file (imports, exports, symbols). Read get_symbol_docs Get JSDoc/TSDoc for a specific symbol. Read grep_search Fast, context-aware text search via ripgrep. Supports context lines and result summarization. Read hygiene_audit Performs a codebase-level hygiene check for technical debt (TODOs) and waste (empty dirs, orphans). Read metabolism_audit Alias for hygiene_audit (Serverless Claw compat). Read search_code Fast regex search via bundled ripgrep (alias for grep_search).

WRITE 1 tools

Write resolve_definition Find where a symbol is defined using TypeScript AST.

EXECUTE 1 tools

Execute build_symbol_index Warm the symbol index for faster navigation.

// RUNNING THIS SERVER

The managed route: connect Ast through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @aiready/ast-mcp-server

// FAQ

How many tools does the Ast MCP server have? +

The Ast MCP server exposes 13 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Ast tools? +

Route the Ast server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Ast tools fall into? +

Ast tools are categorised as Read (11), Write (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.