excel_search_directory
AI agents call excel_search_directory to retrieve information from Excel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations typically retrieve or list data without side effects. Within the context of an Excel manipulation server, searching a directory would enumerate files or sheets rather than modify or execute code. The absence of modifying or destructive language in the name, combined with the 'search' verb, places this squarely in the Read category.
From the tool's definition Tool name contains 'search' and 'directory', typical of retrieval/query operations. No destructive verbs (delete, drop, purge) or modification verbs (create, update, write) present. Description is empty, limiting direct confirmation.
Documented attack patterns abuse exactly the kind of access excel_search_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Excel, and nothing reaches the server without passing your rules. This is the rule we recommend for excel_search_directory:
{
"version": "1",
"default": "deny",
"tools": {
"excel_search_directory": {}
}
}excel_search_directory is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
excel_search_directory. It is categorised as a Read tool in the Excel MCP Server, which means it retrieves data without modifying state.
Register the Excel MCP server in PolicyLayer and add a rule for excel_search_directory: 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 Excel. Nothing to install.
excel_search_directory 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 excel_search_directory 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 excel_search_directory. 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.
excel_search_directory is provided by the Excel MCP server (tangentdomain/excel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Excel, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Excel tools catalogued and risk-classified — across an index of 43,000+ MCP servers.