AI agents use addContactToList to create or update resources in Mailmodo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mailmodo environment.
The tool creates or modifies a contact's list membership, which is reversible (contacts can be removed). This is a Write category operation. Severity is medium because an agent could spam-list users or add contacts without consent, but the effect is not destructive and doesn't involve financial operations. The presence of complementary tools like 'removeContactFromList' confirms this is reversible.
From the tool's definition Tool name 'addContactToList' combined with description 'Add Contact to list' indicates creation/modification of contact list membership. This is a data modification operation.
Attacks that exploit this kind of access
Add Contact to list. It is categorised as a Write tool in the Mailmodo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mailmodo MCP server in PolicyLayer and add a rule for addContactToList: 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 Mailmodo. Nothing to install.
addContactToList 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 addContactToList 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 addContactToList. 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.
addContactToList is provided by the Mailmodo MCP server (mailmodo/mailmodo-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 →