Contacts within a group (resolved by name or resourceName).
AI agents call list_contacts_in_group to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists contact information from a group. It performs a read-only query operation without creating, modifying, deleting, or executing any code. The blast radius is minimal since it only exposes contact data visibility, which is typical for a personal assistant framework managing group membership.
From the tool's definition Tool name is 'list_contacts_in_group' and description states it retrieves 'Contacts within a group' — a query operation with no modification or side effects.
Attacks that exploit this kind of access
Contacts within a group (resolved by name or resourceName). It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for list_contacts_in_group: 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 Nexus Core. Nothing to install.
list_contacts_in_group 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 list_contacts_in_group 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 list_contacts_in_group. 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.
list_contacts_in_group is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →