Remove a contact from a group
AI agents call remove_contact_from_group to permanently remove resources in CiviCRM MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a contact from a group is an irreversible deletion of a relationship record; re-adding requires knowing the prior state. Given CiviCRM groups often control communications, permissions, and membership tracking, misuse can have significant organizational impact.
From the tool's definition 'Remove a contact from a group' — removal of a contact-group association is a destructive, not easily reversible operation that can affect membership, mailing lists, and access controls.
Attacks that exploit this kind of access
Remove a contact from a group. It is categorised as a Destructive tool in the CiviCRM MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CiviCRM MCP Server MCP server in PolicyLayer and add a rule for remove_contact_from_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 CiviCRM MCP Server. Nothing to install.
remove_contact_from_group is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_contact_from_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 remove_contact_from_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.
remove_contact_from_group is provided by the CiviCRM MCP Server MCP server (johncallhub/civicrm-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 →