AI agents call advanced_search to retrieve information from Fastmail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves email data based on search parameters. It does not create, modify, delete, or execute any actions—it only reads and returns matching results. This is a standard Read operation with minimal blast radius if misused (worst case: exposure of email contents the user already has access to).
From the tool's definition Tool name 'advanced_search' and description 'Advanced email search with multiple criteria' indicate a query/retrieval operation with no modification or deletion of data.
Documented attack patterns abuse exactly the kind of access advanced_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fastmail MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for advanced_search:
{
"version": "1",
"default": "deny",
"tools": {
"advanced_search": {}
}
}advanced_search 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.
Advanced email search with multiple criteria. It is categorised as a Read tool in the Fastmail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fastmail MCP Server MCP server in PolicyLayer and add a rule for advanced_search: 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 Fastmail MCP Server. Nothing to install.
advanced_search 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 advanced_search 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 advanced_search. 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.
advanced_search is provided by the Fastmail MCP Server MCP server (madllama25/fastmail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fastmail MCP Server, 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.
38 Fastmail MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.