AI agents call search_symbol to retrieve information from MCP-TY without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only semantic search across a codebase to locate and return information about symbols (classes, functions, variables). It retrieves data without creating, modifying, or deleting any code or project state. Even if an AI agent misuses it by searching for unintended symbols, the worst outcome is exposure of code structure—no side effects or reversible/irreversible changes occur.
From the tool's definition Tool description states 'Search symbols...across the project' - a search/retrieval operation with no modification capability.
Attacks that exploit this kind of access
Search symbols (classes, functions, variables) across the project. It is categorised as a Read tool in the MCP-TY MCP Server, which means it retrieves data without modifying state.
Register the MCP-TY MCP server in PolicyLayer and add a rule for search_symbol: 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 MCP-TY. Nothing to install.
search_symbol 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_symbol 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_symbol. 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_symbol is provided by the MCP-TY MCP server (qinsehm1128/mcp-ty). 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 →