AI agents call search_local_files to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from local files without modifying them. The lack of a description reduces confidence slightly, but the tool name and server context (personal notes, semantic search, file monitoring) clearly indicate a search/retrieval function rather than creation, modification, deletion, or execution.
From the tool's definition Tool name 'search_local_files' indicates retrieval/querying of local file data. Server description emphasizes 'vector search' and semantic indexing of personal notes and files.
Attacks that exploit this kind of access
search_local_files. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for search_local_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 Memory. Nothing to install.
search_local_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_local_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_local_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_local_files is provided by the Memory MCP server (shaktisinhchavda/memory-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 →