Say hello to someone
AI agents call hello_world to retrieve information from Simple MCP Server with Streamable HTTP Example without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to generate a greeting message. It reads or accepts a name input and returns a hello message. No data is written, deleted, executed, or any financial transaction made. Lowest possible blast radius if misused.
From the tool's definition Tool name 'hello_world' and description 'Say hello to someone' indicate a simple greeting output with no side effects.
Attacks that exploit this kind of access
Say hello to someone. It is categorised as a Read tool in the Simple MCP Server with Streamable HTTP Example MCP Server, which means it retrieves data without modifying state.
Register the Simple MCP Server with Streamable HTTP Example MCP server in PolicyLayer and add a rule for hello_world: 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 Simple MCP Server with Streamable HTTP Example. Nothing to install.
hello_world 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 hello_world 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 hello_world. 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.
hello_world is provided by the Simple MCP Server with Streamable HTTP Example MCP server (jonigl/mcp-server-with-streamable-http-example). 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 →