AI agents invoke script_run to trigger actions in ScriptFlow 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.
The tool's primary function is to execute arbitrary scripts. While the actual impact depends on what those scripts do, the Execute category is appropriate because: (1) it triggers external operations (script execution); (2) effects are argument/content-dependent; (3) severity is high because a malicious or misconfigured script could cause significant damage (data loss, credential theft, resource exhaustion, etc.).
From the tool's definition Tool description states 'Execute a script by name'. Combined with sibling tools (script_add, script_edit, script_get, script_list, script_rm) and server context emphasizing 'executable scripts', this tool runs stored code whose effects depend on script…
Documented attack patterns abuse exactly the kind of access script_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScriptFlow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for script_run:
{
"version": "1",
"default": "deny",
"tools": {
"script_run": {
"limits": [
{
"counter": "script_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}script_run 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.
Free to start. No card required.
Execute a script by name. It is categorised as a Execute tool in the ScriptFlow MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScriptFlow MCP Server MCP server in PolicyLayer and add a rule for script_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 ScriptFlow MCP Server. Nothing to install.
script_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 script_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 script_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.
script_run is provided by the ScriptFlow MCP Server MCP server (yanmxa/scriptflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScriptFlow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 ScriptFlow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.