Say hello to the world from http repeat some times
AI agents call say-hello-http to retrieve information from MCP-TS-DEMO 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 simple greeting response over HTTP, repeated a number of times. It reads or produces output without modifying, deleting, or acting on any persistent data. The closest category is Read (or Other), but since it fetches/returns a response, Read is most appropriate. Severity is low as misuse would have negligible impact.
From the tool's definition 'Say hello to the world from http repeat some times' — a greeting/output operation with no data modification, deletion, or financial implications
Attacks that exploit this kind of access
Say hello to the world from http repeat some times. It is categorised as a Read tool in the MCP-TS-DEMO MCP Server, which means it retrieves data without modifying state.
Register the MCP-TS-DEMO MCP server in PolicyLayer and add a rule for say-hello-http: 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 MCP-TS-DEMO. Nothing to install.
say-hello-http 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 say-hello-http 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 say-hello-http. 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.
say-hello-http is provided by the MCP-TS-DEMO MCP server (pjqdyd/mcp-ts-demo). 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 →