Low Risk

search_emails

Search emails with filters (text, sender/recipient, dates, keywords). All filters are AND

How to control search_emails ↓

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

Low Risk

Search is a classic Read operation: it queries a dataset (emails) and returns results without modifying, deleting, or triggering external operations. The blast radius of misuse is minimal — an attacker could search for sensitive emails but cannot modify, delete, or exfiltrate them beyond normal read access.

From the tool's definition Tool description explicitly states 'Search emails with filters' — a query operation that retrieves data. No mutations or side effects are mentioned.

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

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

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

search_emails 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 JMAP MCP — 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_emails tool do? +

Search emails with filters (text, sender/recipient, dates, keywords). All filters are AND. It is categorised as a Read tool in the JMAP MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_emails? +

Register the JMAP 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 JMAP MCP. Nothing to install.

What risk level is search_emails? +

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

Can I rate-limit search_emails? +

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.

How do I block search_emails completely? +

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.

What MCP server provides search_emails? +

search_emails is provided by the JMAP MCP server (wyattjoh/jmap-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every JMAP MCP tool call.

Deterministic rules across all 11 JMAP MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

11 JMAP MCP 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.