run_contam_simulation · CONTAM MCP: Risk & Policy

WHAT IT DOES

What run_contam_simulation does on CONTAM MCP

AI agents invoke run_contam_simulation to trigger actions in CONTAM MCP. 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 run_contam_simulation needs a policy

This tool executes external simulation software (CONTAM/ContamX) with user-supplied project files. While the immediate output is data collection rather than system commands, the tool triggers computational processes whose results depend entirely on model inputs and could produce unexpected outcomes if a malicious or malformed .prj file is supplied.

From the tool's definition The tool description states it "run[s] a CONTAM .prj model" and "collect[s] the generated files." The verb 'run' combined with executing a simulation model indicates code/model execution whose effects depend on arguments (the specific .prj file and simulation…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_contam_simulation Rate-limited

run_contam_simulation 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": {
    "run_contam_simulation": {
      "limits": [
        {
          "counter": "run_contam_simulation_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 CONTAM MCP, so you can run agents against it safely.

FAQ

Questions about run_contam_simulation

What does the run_contam_simulation tool do? +

Use this when you want to validate or run a CONTAM .prj model with ContamX and collect the generated files. It is categorised as a Execute tool in the CONTAM MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_contam_simulation? +

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

What risk level is run_contam_simulation? +

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

Can I rate-limit run_contam_simulation? +

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

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

run_contam_simulation is provided by the CONTAM MCP server (summer521521/contam_plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.