approve_learned_workflow · Qontinui Web MCP Server MCP

WHAT IT DOES

What approve_learned_workflow does on Qontinui Web MCP Server

AI agents use approve_learned_workflow to create or update resources in Qontinui Web MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qontinui Web MCP Server environment.

WHY IT NEEDS A POLICY

Why approve_learned_workflow needs a policy

Approving a workflow transitions it from a pending/draft state to approved status, and publishing makes it active for automation execution. While not destructive (reversible via unapprove/unpublish), this is a write operation that modifies configuration state and enables automated actions.

From the tool's definition The tool performs 'approve' and 'optionally publish' operations on a learned workflow, which are irreversible state transitions that modify workflow status and potentially make it available to users.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_learned_workflow Rate-limited

approve_learned_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "approve_learned_workflow": {
      "limits": [
        {
          "counter": "approve_learned_workflow_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Qontinui Web MCP Server, so you can run agents against it safely.

FAQ

Questions about approve_learned_workflow

What does the approve_learned_workflow tool do? +

Approve a learned workflow and optionally publish it to the project. It is categorised as a Write tool in the Qontinui Web MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_learned_workflow? +

Register the Qontinui Web MCP Server MCP server in PolicyLayer and add a rule for approve_learned_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 Qontinui Web MCP Server. Nothing to install.

What risk level is approve_learned_workflow? +

approve_learned_workflow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit approve_learned_workflow? +

Yes. Add a rate_limit block to the approve_learned_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.

How do I block approve_learned_workflow completely? +

Set action: deny in the PolicyLayer policy for approve_learned_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.

What MCP server provides approve_learned_workflow? +

approve_learned_workflow is provided by the Qontinui Web MCP Server MCP server (qontinui/qontinui-web-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.