AI agents use script_add 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 creates new executable scripts that can be run by script_run. While creation itself is Write-level, the high severity reflects that scripts added here become part of a workflow management system where they can be executed (script_run) by AI agents. Maliciously crafted scripts could cause significant harm when executed, but the tool itself only performs reversible creation, not execution or deletion.
From the tool's definition The tool "script_add" creates a new script in the repository. The description explicitly states 'Add a new script to the repository', which is a create operation that modifies the script repository state reversibly.
Documented attack patterns abuse exactly the kind of access script_add 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_add:
{
"version": "1",
"default": "deny",
"tools": {
"script_add": {
"limits": [
{
"counter": "script_add_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}script_add 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.
Add a new script to the repository. 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_add: 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_add 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_add 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_add. 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_add 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.