Add contacts to a mailing list.
AI agents use add_contacts to create or update resources in XEM Email MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your XEM Email MCP Server environment.
This tool creates or modifies contact records within a mailing list, which is a reversible write operation. It does not execute arbitrary code, delete data permanently, or move money. Severity is medium because unauthorized bulk contact additions could enable spam campaigns or unauthorized marketing, but the operation itself is reversible and does not cause permanent data loss or financial harm.
From the tool's definition Tool name 'add_contacts' and description 'Add contacts to a mailing list' indicate creation/modification of contact data.
Attacks that exploit this kind of access
Add contacts to a mailing list. It is categorised as a Write tool in the XEM Email MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the XEM Email MCP Server MCP server in PolicyLayer and add a rule for add_contacts: 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 XEM Email MCP Server. Nothing to install.
add_contacts 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 add_contacts 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 add_contacts. 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.
add_contacts is provided by the XEM Email MCP Server MCP server (mailxem/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 →