Greet a user by name
AI agents call greet_user to retrieve information from MCPServer (FastMCP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a name as input and produces a greeting message. It reads/uses the provided input to construct a response without modifying any data, executing commands, or causing any external effects. Lowest possible blast radius.
From the tool's definition 'Greet a user by name' — purely generates and returns a greeting string with no side effects
Attacks that exploit this kind of access
Greet a user by name. It is categorised as a Read tool in the MCPServer (FastMCP) MCP Server, which means it retrieves data without modifying state.
Register the MCPServer (FastMCP) MCP server in PolicyLayer and add a rule for greet_user: 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 MCPServer (FastMCP). Nothing to install.
greet_user 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 greet_user 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 greet_user. 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.
greet_user is provided by the MCPServer (FastMCP) MCP server (justineqinlao/mcpserver). 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 →