Search and retrieve contacts from CiviCRM including custom fields
AI agents call get_contacts to retrieve information from CiviCRM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval operations only. It searches and fetches contact records without creating, modifying, or deleting data. The absence of write or destructive operations, combined with the explicit 'retrieve' language, clearly places this in the Read category. Severity is low because querying contact data has minimal security blast radius compared to tools that modify or delete records.
From the tool's definition Tool name 'get_contacts' with description 'Search and retrieve contacts from CiviCRM including custom fields' uses retrieval verbs (search, retrieve) with no modification or deletion capabilities mentioned.
Attacks that exploit this kind of access
Search and retrieve contacts from CiviCRM including custom fields. It is categorised as a Read tool in the CiviCRM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CiviCRM MCP Server MCP server in PolicyLayer and add a rule for get_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 CiviCRM MCP Server. Nothing to install.
get_contacts 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_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 get_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.
get_contacts 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 →