Search text or regex patterns across the workspace when semantic symbol lookup is not enough. Prefer code.find_symbol plus trace tools for symbols; read only returned top files. Language filters: ${SUPPORTED_LANGUAGE_FILTERS}.
AI agents call code.search_text to retrieve information from Navigation Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only text/regex search operation across code files in the workspace. It retrieves and returns matching results but does not create, modify, delete, or execute anything. The explicit mention of "read only" and lack of any write or execute semantics clearly classifies it as a Read operation with low severity since misuse would only expose information already in the codebase.
From the tool's definition Tool description explicitly states "read only returned top files" and describes a search operation across the workspace with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search text or regex patterns across the workspace when semantic symbol lookup is not enough. Prefer code.find_symbol plus trace tools for symbols; read only returned top files. Language filters: ${SUPPORTED_LANGUAGE_FILTERS}. It is categorised as a Read tool in the Navigation Agent MCP Server, which means it retrieves data without modifying state.
Register the Navigation Agent MCP server in PolicyLayer and add a rule for code.search_text: 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 Navigation Agent. Nothing to install.
code.search_text 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 code.search_text 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 code.search_text. 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.
code.search_text is provided by the Navigation Agent MCP server (j0k3r-dev-rgl/navigation-agent-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 →