AI agents use set_default_account to create or update resources in Email — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Email environment.
This tool modifies persistent application state (the default account setting) but does not create, delete, or move actual data. It is reversible (can be changed again), so it is not Destructive. It has no financial impact and does not execute arbitrary code.
From the tool's definition Tool performs state modification by setting a default account preference. The description explicitly states it 'set[s] the default account', which is a write operation that persists configuration state.
Attacks that exploit this kind of access
Set the default account (used when account is omitted). It is categorised as a Write tool in the Email MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Email MCP server in PolicyLayer and add a rule for set_default_account: 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 Email. Nothing to install.
set_default_account 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 set_default_account 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 set_default_account. 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.
set_default_account is provided by the Email MCP server (swapnilsurdi/email_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →