AI agents call get_contact_details to retrieve information from CRM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly signals a query/retrieval operation with no side effects. In a CRM context, retrieving contact details is a standard Read operation that queries existing data. Without a description, confidence is slightly reduced, but the naming pattern and sibling tools provide sufficient evidence. Severity is low because misuse would only expose existing data, not modify or delete it.
From the tool's definition Tool name 'get_contact_details' indicates retrieval of contact information. The description is empty, but based on naming convention and context within a CRM server offering 'full CRUD operations' with sibling tools like 'get_contact_history' and…
Documented attack patterns abuse exactly the kind of access get_contact_details gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CRM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_contact_details:
{
"version": "1",
"default": "deny",
"tools": {
"get_contact_details": {}
}
}get_contact_details is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_contact_details. It is categorised as a Read tool in the CRM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CRM MCP Server MCP server in PolicyLayer and add a rule for get_contact_details: 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 CRM MCP Server. Nothing to install.
get_contact_details 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_contact_details 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_contact_details. 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_contact_details is provided by the CRM MCP Server MCP server (nxt3d/mcp-crm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CRM MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 CRM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.