Get IDs of emails created, updated, or destroyed since a previous state. Use the state string from a get_emails response. Supports optional auto-fetching of full email details. If the state is too old, falls back with an error suggesting a fresh search_emails call.
AI agents call get_email_changes 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.
This tool queries email metadata and state changes to identify what has been created, updated, or destroyed, then optionally retrieves the corresponding email details. It is purely informational—it reads data about email changes without modifying, deleting, or executing anything. The reference to 'destroyed' emails describes what happened in the past, not an action this tool performs.
From the tool's definition Tool description states it 'Get[s] IDs of emails created, updated, or destroyed since a previous state' and provides optional 'auto-fetching of full email details'.
Documented attack patterns abuse exactly the kind of access get_email_changes 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 get_email_changes:
{
"version": "1",
"default": "deny",
"tools": {
"get_email_changes": {}
}
}get_email_changes 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.
Get IDs of emails created, updated, or destroyed since a previous state. Use the state string from a get_emails response. Supports optional auto-fetching of full email details. If the state is too old, falls back with an error suggesting a fresh search_emails call. It is categorised as a Read tool in the JMAP MCP MCP Server, which means it retrieves data without modifying state.
Register the JMAP MCP server in PolicyLayer and add a rule for get_email_changes: 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.
get_email_changes 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 get_email_changes 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 get_email_changes. 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.
get_email_changes 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.
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.