AI agents call peopleByEmail to retrieve information from Routine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward read/lookup operation returning contact data associated with an email address. It has no capability to modify, delete, or execute actions. The blast radius if misused by an AI agent would be limited to potential privacy concerns from contact enumeration, but no data destruction, financial impact, or code execution risk exists.
From the tool's definition Tool description states 'The potential contact owning this email address' - a query operation that retrieves contact information based on email lookup with no modification or side effects.
Attacks that exploit this kind of access
The potential contact owning this email address. It is categorised as a Read tool in the Routine MCP Server, which means it retrieves data without modifying state.
Register the Routine MCP server in PolicyLayer and add a rule for peopleByEmail: 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 Routine. Nothing to install.
peopleByEmail 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 peopleByEmail 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 peopleByEmail. 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.
peopleByEmail is provided by the Routine MCP server (routineco/mcp-server). 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 →