Get details of a customer contact (name, account, phone, email)
AI agents call get_csm_contact to retrieve information from ServiceNow-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple data retrieval operation on customer contact records. While phone and email information may be considered sensitive PII, the tool itself has no mechanism to modify, delete, or misuse that data—it only fetches it.
From the tool's definition Tool retrieves contact details (name, account, phone, email) with no indication of modification, deletion, or side effects. The word 'Get' and verb 'retrieves' in the description indicate a data query operation.
Attacks that exploit this kind of access
Get details of a customer contact (name, account, phone, email). It is categorised as a Read tool in the ServiceNow-MCP MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow- MCP server in PolicyLayer and add a rule for get_csm_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 ServiceNow-MCP. Nothing to install.
get_csm_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_csm_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_csm_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_csm_contact is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-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 →