Mark emails as read/unread or flagged/unflagged. You can update multiple keywords at once.
AI agents use mark_emails to create or update resources in JMAP MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JMAP MCP environment.
This tool modifies email state (read/unread/flagged status) but the changes are reversible—emails can be unmarked, flags can be removed, etc. This qualifies as Write rather than Destructive. The severity is medium because an agent could mark many emails as read (losing visibility), but email data itself remains intact and the action is undoable. Confidence is high due to explicit description of the mutation behavior.
From the tool's definition Tool description states 'Mark emails as read/unread or flagged/unflagged. You can update multiple keywords at once.' The verbs 'mark' and 'update' indicate modification of email metadata.
Documented attack patterns abuse exactly the kind of access mark_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 mark_emails:
{
"version": "1",
"default": "deny",
"tools": {
"mark_emails": {
"limits": [
{
"counter": "mark_emails_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_emails stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark emails as read/unread or flagged/unflagged. You can update multiple keywords at once. It is categorised as a Write tool in the JMAP MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JMAP MCP server in PolicyLayer and add a rule for mark_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.
mark_emails is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mark_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 mark_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.
mark_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.
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.