inject_scenario · Rockfish MCP Server MCP: Risk & Policy

WHAT IT DOES

What inject_scenario does on Rockfish MCP Server

AI agents invoke inject_scenario to trigger actions in Rockfish 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 inject_scenario needs a policy

Injecting an anomaly scenario is an active operation that triggers external effects within the ML platform (modifying data pipelines, models, or monitoring systems). It is not a simple read, nor is it a straightforward reversible write — it executes a scenario that could affect running workflows, datasets, or models.

From the tool's definition 'Inject a synthetic anomaly scenario and optionally generate tests' — 'inject' and 'scenario' indicate triggering an external operation that modifies system state by introducing synthetic anomalies into the ML platform

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

inject_scenario Rate-limited

inject_scenario 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": {
    "inject_scenario": {
      "limits": [
        {
          "counter": "inject_scenario_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 Rockfish MCP Server, so you can run agents against it safely.

FAQ

Questions about inject_scenario

What does the inject_scenario tool do? +

Inject a synthetic anomaly scenario and optionally generate tests. It is categorised as a Execute tool in the Rockfish 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 inject_scenario? +

Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for inject_scenario: 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 Rockfish MCP Server. Nothing to install.

What risk level is inject_scenario? +

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

Can I rate-limit inject_scenario? +

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

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

inject_scenario is provided by the Rockfish MCP Server MCP server (wolfdancer/rockfish-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.