Search for text within files in a directory (recursive)
AI agents call search_files to retrieve information from Local Dev Bridge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and searches data within files. It has no side effects, does not modify files, does not execute code, and does not delete anything. It is a straightforward read operation with minimal risk even if misused by an agent, as the worst outcome would be information disclosure of already-accessible local files.
From the tool's definition Tool name is 'search_files' and description states it 'Search for text within files in a directory (recursive)' — a pure read operation that queries file contents without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Search for text within files in a directory (recursive). It is categorised as a Read tool in the Local Dev Bridge MCP MCP Server, which means it retrieves data without modifying state.
Register the Local Dev Bridge MCP server in PolicyLayer and add a rule for search_files: 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 Dev Bridge MCP. Nothing to install.
search_files 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_files 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_files. 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_files is provided by the Local Dev Bridge MCP server (talentedmrweb/local-dev-bridge-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 →