analysis_start · Oncallhealth MCP: Risk & Policy

WHAT IT DOES

What analysis_start does on Oncallhealth

AI agents invoke analysis_start to trigger actions in Oncallhealth. 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 analysis_start needs a policy

This tool executes a defined operation (health analysis) whose effects depend on when it is invoked and what data exists in the system at that time. While the action itself is not destructive or financial, it triggers a background process with observable side effects (consuming resources, generating results, potentially affecting system state).

From the tool's definition Tool name 'analysis_start' and description 'Start a new health analysis' indicates the tool initiates a process that triggers an operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

analysis_start Rate-limited

analysis_start 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": {
    "analysis_start": {
      "limits": [
        {
          "counter": "analysis_start_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 Oncallhealth, so you can run agents against it safely.

FAQ

Questions about analysis_start

What does the analysis_start tool do? +

Start a new health analysis. It is categorised as a Execute tool in the Oncallhealth MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on analysis_start? +

Register the Oncallhealth MCP server in PolicyLayer and add a rule for analysis_start: 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 Oncallhealth. Nothing to install.

What risk level is analysis_start? +

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

Can I rate-limit analysis_start? +

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

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

analysis_start is provided by the Oncallhealth MCP server (rootly-ai-labs/mcp-on-call-health). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.