Get email threads by their IDs. Thread IDs are available from get_emails responses (threadId property). Returns a list of email IDs in each thread — use get_emails on those IDs to fetch the actual email content.
AI agents call get_threads 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.
get_threads is a read-only operation that queries and retrieves thread metadata (email IDs). It does not create, modify, delete, or execute anything. The tool fits the Read category definition: 'retrieves or queries data; no side effects'.
From the tool's definition Tool retrieves email threads by IDs and returns a list of email IDs in each thread. The description explicitly states it 'Returns a list of email IDs in each thread' with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access get_threads 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_threads:
{
"version": "1",
"default": "deny",
"tools": {
"get_threads": {}
}
}get_threads 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 email threads by their IDs. Thread IDs are available from get_emails responses (threadId property). Returns a list of email IDs in each thread — use get_emails on those IDs to fetch the actual email content. 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_threads: 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_threads 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_threads 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_threads. 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_threads 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.