Search text in readable source files inside an allowed project root.
AI agents call mcp_search_text to retrieve information from Local Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data (searching text content) without side effects. It operates only on readable files within allowed project roots, has no ability to modify, delete, or execute code, and poses minimal risk if misused by an AI agent — worst case is information disclosure of already-accessible source code.
From the tool's definition Tool description states it 'Search text in readable source files' — a query/search operation with no modification, deletion, or execution capability.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Search text in readable source files inside an allowed project root. It is categorised as a Read tool in the Local Code MCP Server, which means it retrieves data without modifying state.
Register the Local Code MCP server in PolicyLayer and add a rule for mcp_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 Local Code. Nothing to install.
mcp_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 mcp_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 mcp_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.
mcp_search_text is provided by the Local Code MCP server (js190-prog/local-code-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 →