Get the primary contact for a client
AI agents call get_client_primary_contact to retrieve information from Campaign Monitor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact information from the Campaign Monitor system without creating, modifying, deleting, or executing any operations. It is a straightforward query operation that returns existing data. The severity is low because access to a single contact record poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get_client_primary_contact' and description 'Get the primary contact for a client' indicate a retrieval operation with no side effects or modifications.
Attacks that exploit this kind of access
Get the primary contact for a client. It is categorised as a Read tool in the Campaign Monitor MCP MCP Server, which means it retrieves data without modifying state.
Register the Campaign Monitor MCP server in PolicyLayer and add a rule for get_client_primary_contact: 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 Campaign Monitor MCP. Nothing to install.
get_client_primary_contact 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 get_client_primary_contact 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 get_client_primary_contact. 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.
get_client_primary_contact is provided by the Campaign Monitor MCP server (pauliowest/cmon-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 →