start_span · Metis Public Health MCP: Risk & Policy

WHAT IT DOES

What start_span does on Metis Public Health

AI agents call start_span as a supporting operation in Metis Public Health workflows.

WHY IT NEEDS A POLICY

Why start_span needs a policy

The description is entirely empty, making it impossible to determine what this tool does from its description. The name 'start_span' could refer to starting a tracing/telemetry span (observability instrumentation), which would be a low-risk read/other operation. Given the context of a public health research server with PDF indexing and specialist agents, it may relate to text span marking or tracing.

From the tool's definition Tool name is 'start_span' and description is empty or uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_span Rate-limited

start_span gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_span": {
      "limits": [
        {
          "counter": "start_span_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about start_span

What does the start_span tool do? +

start_span. It is categorised as a Other tool in the Metis Public Health MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on start_span? +

Register the Metis Public Health MCP server in PolicyLayer and add a rule for start_span: 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 Metis Public Health. Nothing to install.

What risk level is start_span? +

start_span is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit start_span? +

Yes. Add a rate_limit block to the start_span 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 start_span completely? +

Set action: deny in the PolicyLayer policy for start_span. 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 start_span? +

start_span is provided by the Metis Public Health MCP server (sveritg/metis_ph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.