multi-greet · Streamable HTTP MCP Server MCP: Risk & Policy

WHAT IT DOES

What multi-greet does on Streamable HTTP MCP Server

AI agents invoke multi-greet to trigger actions in Streamable HTTP MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why multi-greet needs a policy

The tool sends multiple greetings with delays, implying it triggers timed/sequential external operations rather than a simple single read. The delays and streaming behavior indicate it executes a process over time, placing it in Execute rather than Read or Write. Blast radius is low as it only produces greeting messages.

From the tool's definition sends different greetings with delays between them

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

multi-greet Rate-limited

multi-greet stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "multi-greet": {
      "limits": [
        {
          "counter": "multi-greet_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Streamable HTTP MCP Server, so you can run agents against it safely.

FAQ

Questions about multi-greet

What does the multi-greet tool do? +

A tool that sends different greetings with delays between them. It is categorised as a Execute tool in the Streamable HTTP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on multi-greet? +

Register the Streamable HTTP MCP Server MCP server in PolicyLayer and add a rule for multi-greet: 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 Streamable HTTP MCP Server. Nothing to install.

What risk level is multi-greet? +

multi-greet is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit multi-greet? +

Yes. Add a rate_limit block to the multi-greet 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 multi-greet completely? +

Set action: deny in the PolicyLayer policy for multi-greet. 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 multi-greet? +

multi-greet is provided by the Streamable HTTP MCP Server MCP server (rmavuluri/streamable-http-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.