AI agents call search_emails to retrieve information from Zoho Mail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email metadata (messageId and folderId) based on search criteria without modifying, deleting, or executing any operations. It is a standard read/query operation with no side effects. The severity is low because email metadata disclosure, while potentially sensitive, is limited to what the user already has access to in their own inbox.
From the tool's definition Tool performs search inbox by keyword, sender email, or subject fragment — returns messageId and folderId for use with read_email. No modification, deletion, or execution occurs; purely retrieval and querying of existing email metadata.
Attacks that exploit this kind of access
Search inbox by keyword, sender email, or subject fragment — returns messageId and folderId for use with read_email. It is categorised as a Read tool in the Zoho Mail MCP Server, which means it retrieves data without modifying state.
Register the Zoho Mail MCP server in PolicyLayer and add a rule for search_emails: 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 Zoho Mail. Nothing to install.
search_emails 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_emails 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_emails. 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_emails is provided by the Zoho Mail MCP server (sirgreed808/zoho-mail-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 →