run_model · Mcp Fal MCP: Risk & Policy

WHAT IT DOES

What run_model does on Mcp Fal

AI agents invoke run_model to trigger actions in Mcp Fal. 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_model needs a policy

The tool executes external code/models on the Fal.ai platform with caller-controlled parameters. This is an Execute category risk because it triggers external operations whose effects depend on the arguments provided.

From the tool's definition Tool description states 'Run any Fal.ai model' with 'arbitrary input parameters', indicating arbitrary execution of external models.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_model Rate-limited

run_model 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_model": {
      "limits": [
        {
          "counter": "run_model_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 Mcp Fal, so you can run agents against it safely.

FAQ

Questions about run_model

What does the run_model tool do? +

Run any Fal.ai model by its model ID with arbitrary input parameters. It is categorised as a Execute tool in the Mcp Fal 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_model? +

Register the Mcp Fal MCP server in PolicyLayer and add a rule for run_model: 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 Mcp Fal. Nothing to install.

What risk level is run_model? +

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

Can I rate-limit run_model? +

Yes. Add a rate_limit block to the run_model 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_model completely? +

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

run_model is provided by the Mcp Fal MCP server (mohsenmousavieyeline/mcp-fal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.