AI agents call trw_code_search to retrieve information from Trw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Code search is fundamentally a read operation that retrieves or queries code data without modifying, deleting, or executing anything. The empty description lowers confidence slightly, but the semantic name and server context strongly indicate this is a benign search/query tool. Classified as Read with low severity since search operations have minimal blast radius.
From the tool's definition Tool name 'trw_code_search' suggests a search operation. The pattern matches sibling tools like 'trw_code_symbol' and 'trw_code_index_update', which are read-oriented code analysis tools.
Attacks that exploit this kind of access
trw_code_search. It is categorised as a Read tool in the Trw MCP Server, which means it retrieves data without modifying state.
Register the Trw MCP server in PolicyLayer and add a rule for trw_code_search: 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 Trw. Nothing to install.
trw_code_search 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 trw_code_search 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 trw_code_search. 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.
trw_code_search is provided by the Trw MCP server (wallter/trw-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 →