Search code using AST pattern matching with metavariables ($VAR for capture, $$VAR for single anonymous, $$$VAR for multiple)
AI agents call search_ast_pattern to retrieve information from Code Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information about code structure through AST (Abstract Syntax Tree) pattern matching. It has no side effects - it does not create, modify, delete, or execute code. It belongs in the Read category as it performs information retrieval and analysis only.
From the tool's definition Tool performs 'Search code using AST pattern matching' - a query operation that retrieves and analyzes code structure without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Search code using AST pattern matching with metavariables ($VAR for capture, $$VAR for single anonymous, $$$VAR for multiple). It is categorised as a Read tool in the Code Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Code Search MCP server in PolicyLayer and add a rule for search_ast_pattern: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Code Search MCP. Nothing to install.
search_ast_pattern is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_ast_pattern rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_ast_pattern. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_ast_pattern is provided by the Code Search MCP server (llmtooling/code-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →