Submit one fal model run. Default wait=submit returns request ids immediately, then use fal_request to wait, inspect status, or fetch the final result.
AI agents invoke fal_run to trigger actions in Simple 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.
This tool executes arbitrary fal models with user-supplied parameters. While it doesn't directly run shell commands, it triggers computational workflows on external systems whose behavior and side effects are determined by the model configuration and input arguments.
From the tool's definition The tool description states 'Submit one fal model run' and mentions execution of fal models. The design pattern of immediate submission followed by status checking via fal_request indicates this triggers external model execution whose effects depend on the…
Attacks that exploit this kind of access
Submit one fal model run. Default wait=submit returns request ids immediately, then use fal_request to wait, inspect status, or fetch the final result. It is categorised as a Execute tool in the Simple Fal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simple Fal MCP server in PolicyLayer and add a rule for fal_run: 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 Simple Fal. Nothing to install.
fal_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the fal_run 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.
Set action: deny in the PolicyLayer policy for fal_run. 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.
fal_run is provided by the Simple Fal MCP server (pintar-team/simple-fal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →