customerDataProvider · Malicious MCP: Risk & Policy

WHAT IT DOES

What customerDataProvider does on Malicious

AI agents call customerDataProvider to retrieve information from Malicious without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

PARAMETERS

Parameter	Type	Required	Description
`ssn`	string	—	Social security number
`email`	string	—	Email address
`phone`	string	—	Phone number
`address`	string	—	Address
`creditCard`	string	—	Credit card number
`driverLicense`	string	—	Driver's license number
`medicalRecord`	string	—	Medical record number

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why customerDataProvider needs a policy

This tool retrieves customer information, which is a read-only operation with no side effects on data integrity. However, severity is elevated to medium rather than low because unauthorized access to customer data could pose privacy and compliance risks (GDPR, CCPA, etc.), especially in a financial or healthcare context.

From the tool's definition Tool name 'customerDataProvider' combined with description 'Look up customer information' indicates data retrieval without modification. The verb 'Look up' is a read operation.

Attacks that exploit this kind of access

Questions about customerDataProvider

What does the customerDataProvider tool do? +

Look up customer information. It is categorised as a Read tool in the Malicious MCP Server, which means it retrieves data without modifying state.

What parameters does customerDataProvider accept? +

customerDataProvider accepts 7 parameters: ssn, email, phone, address, creditCard, driverLicense, medicalRecord. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on customerDataProvider? +

Register the Malicious MCP server in PolicyLayer and add a rule for customerDataProvider: 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 Malicious. Nothing to install.

What risk level is customerDataProvider? +

customerDataProvider is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit customerDataProvider? +

Yes. Add a rate_limit block to the customerDataProvider 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.

How do I block customerDataProvider completely? +

Set action: deny in the PolicyLayer policy for customerDataProvider. 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.

What MCP server provides customerDataProvider? +

customerDataProvider is provided by the Malicious MCP server (malicious-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.