Low Risk

search_directory

search_directory

How to control search_directory ↓

AI agents call search_directory to retrieve information from MCP Google Contacts Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This is a read operation that queries and retrieves contact/directory information from Google Workspace. While the description is empty, the server's documented purpose ('search Google Workspace directories') and the naming convention ('search_') clearly indicate a retrieval operation with no side effects.

From the tool's definition Tool name 'search_directory' combined with server context showing it searches Google Workspace directories. Server description states 'search Google Workspace directories' and lists search_contacts as a sibling tool.

Documented attack patterns abuse exactly the kind of access search_directory gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Google Contacts Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_directory:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_directory": {}
  }
}

search_directory is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register MCP Google Contacts Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_directory tool do? +

search_directory. It is categorised as a Read tool in the MCP Google Contacts Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_directory? +

Register the MCP Google Contacts Server MCP server in PolicyLayer and add a rule for 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 MCP Google Contacts Server. Nothing to install.

What risk level is search_directory? +

search_directory is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_directory? +

Yes. Add a rate_limit block to the 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.

How do I block search_directory completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides search_directory? +

search_directory is provided by the MCP Google Contacts Server MCP server (rayanzaki/mcp-google-contacts-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Google Contacts Server tool call.

Deterministic rules across all 9 MCP Google Contacts Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

9 MCP Google Contacts Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.