Returns list of all customers currently at high risk of churn. THIS REQUIRES DATABASE ACCESS - Claude cannot do this alone!
AI agents call get_high_risk_customers to retrieve information from Sentiment Evolution Tracker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it retrieves customer risk data from a database. Severity is medium rather than low because the sensitive nature of the data returned (high-risk customer identities and churn predictions) could enable harmful downstream actions if misused by an AI agent (e.g., targeting vulnerable customers for predatory practices, or exposing PII).
From the tool's definition Tool returns a list of customers 'currently at high risk of churn' - it retrieves and queries data without modifying, deleting, or executing external operations. The description indicates data retrieval ('Returns list'), not creation or deletion.
Attacks that exploit this kind of access
Returns list of all customers currently at high risk of churn. THIS REQUIRES DATABASE ACCESS - Claude cannot do this alone!. It is categorised as a Read tool in the Sentiment Evolution Tracker MCP Server, which means it retrieves data without modifying state.
Register the Sentiment Evolution Tracker MCP server in PolicyLayer and add a rule for get_high_risk_customers: 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 Sentiment Evolution Tracker. Nothing to install.
get_high_risk_customers 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_high_risk_customers 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_high_risk_customers. 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_high_risk_customers is provided by the Sentiment Evolution Tracker MCP server (rubenreyesss/mcp-nlp-analytics). 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 →