Start or stop recording a workflow. All actions between start/stop are saved.
AI agents use record_workflow to create or update resources in Openowl — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openowl environment.
This tool records and saves a workflow (sequences of desktop actions). It creates/writes a persistent workflow artifact. While the recorded actions themselves could be destructive or financial when replayed, the recording action itself is a Write operation — it captures and stores data.
From the tool's definition 'Start or stop recording a workflow. All actions between start/stop are saved.'
Documented attack patterns abuse exactly the kind of access record_workflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openowl, and nothing reaches the server without passing your rules. This is the rule we recommend for record_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"record_workflow": {
"limits": [
{
"counter": "record_workflow_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}record_workflow 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.
Start or stop recording a workflow. All actions between start/stop are saved. It is categorised as a Write tool in the Openowl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openowl MCP server in PolicyLayer and add a rule for record_workflow: 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 Openowl. Nothing to install.
record_workflow 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 record_workflow 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 record_workflow. 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.
record_workflow is provided by the Openowl MCP server (mihir-kanzariya/openowl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openowl, 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.
40 Openowl tools catalogued and risk-classified — across an index of 43,000+ MCP servers.