search_folder
AI agents call search_folder to retrieve information from Zimbra MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve and filter existing data without modifying, deleting, or executing arbitrary code. Even with access to email folder contents, the blast radius is limited to information disclosure of data the user already has access to. Low confidence (0.85 rather than higher) reflects the empty tool description, but the name and server context strongly suggest a benign read operation.
From the tool's definition Tool name 'search_folder' combined with server capability to 'search' emails and folders; sibling tools include read-only operations like 'get_calendar_events' and 'download_attachment'.
Attacks that exploit this kind of access
search_folder. It is categorised as a Read tool in the Zimbra MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zimbra MCP Server MCP server in PolicyLayer and add a rule for search_folder: 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 Zimbra MCP Server. Nothing to install.
search_folder 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_folder 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_folder. 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_folder is provided by the Zimbra MCP Server MCP server (jeremie-lesage/zimbra-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 →