search_declarations
AI agents call search_declarations to retrieve information from Code Declaration Lookup MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches code metadata from an indexed database. It has no ability to modify, delete, or execute code—only to query and return results. The blast radius of misuse is minimal: worst case, an AI agent performs redundant or noisy searches. No side effects, no data modification, no code execution.
From the tool's definition Tool is part of a code declaration lookup server that enables 'full-text search for code declarations across multiple languages using SQLite FTS5'.
Attacks that exploit this kind of access
search_declarations. It is categorised as a Read tool in the Code Declaration Lookup MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Code Declaration Lookup MCP Server MCP server in PolicyLayer and add a rule for search_declarations: 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 Declaration Lookup MCP Server. Nothing to install.
search_declarations 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_declarations 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_declarations. 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_declarations is provided by the Code Declaration Lookup MCP Server MCP server (osinmv/function-lookup-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 →