get_user_referrer
AI agents call get_user_referrer to retrieve information from Fuul 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 and referrer lookup context indicate data retrieval with no side effects. Classified as Read. Severity is medium rather than low because referrer data in affiliate systems can include sensitive relationship mappings and commission tracking information that could enable fraud if misused by an agent (e.g., attributing sales to wrong affiliates).
From the tool's definition Tool name 'get_user_referrer' with no description provided. Based on naming convention ('get_*') and context within an affiliate/analytics platform, this retrieves referrer information for a user.
Attacks that exploit this kind of access
get_user_referrer. It is categorised as a Read tool in the Fuul MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fuul MCP Server MCP server in PolicyLayer and add a rule for get_user_referrer: 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 Fuul MCP Server. Nothing to install.
get_user_referrer 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_user_referrer 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_user_referrer. 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_user_referrer is provided by the Fuul MCP Server MCP server (kuyen-labs/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 →