AI agents use script_edit to create or update resources in ScriptFlow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ScriptFlow MCP Server environment.
This tool modifies scripts persistently but reversibly—the change can be undone by editing again. However, severity is high because scripts can contain arbitrary logic that runs via script_run; editing a script could alter its behavior dangerously. It does not irreversibly delete (that is script_rm) nor directly execute code (that is script_run), so Write is the correct category.
From the tool's definition Tool name 'script_edit' and description 'Edit an existing script' indicate modification of existing stored scripts without deletion. Related destructive tool 'script_rm' exists separately, confirming this tool is reversible modification only.
Documented attack patterns abuse exactly the kind of access script_edit 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_edit:
{
"version": "1",
"default": "deny",
"tools": {
"script_edit": {
"limits": [
{
"counter": "script_edit_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}script_edit stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Edit an existing script. It is categorised as a Write tool in the ScriptFlow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ScriptFlow MCP Server MCP server in PolicyLayer and add a rule for script_edit: 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_edit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the script_edit 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_edit. 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_edit 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.