skill · Workflows MCP Server MCP: Risk & Policy

WHAT IT DOES

What skill does on Workflows MCP Server

AI agents invoke skill to trigger actions in Workflows 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.

WHY IT NEEDS A POLICY

Why skill needs a policy

This tool appears to enable execution of arbitrary Python workflows within an automation context. Combined with the server's stated ability to let AI 'build and modify automation workflows themselves', this represents Execute-level risk: the tool can trigger external operations (Python script execution) whose effects depend entirely on the script arguments/content.

From the tool's definition Server description states 'create, manage, and execute independent Python workflow scripts' and 'AI to build and modify automation workflows themselves'. Tool is sibling to 'execute_skill_script' indicating execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skill Rate-limited

skill 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "skill": {
      "limits": [
        {
          "counter": "skill_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about skill

What does the skill tool do? +

skill. It is categorised as a Execute tool in the Workflows MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on skill? +

Register the Workflows MCP Server MCP server in PolicyLayer and add a rule for skill: 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 Workflows MCP Server. Nothing to install.

What risk level is skill? +

skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit skill? +

Yes. Add a rate_limit block to the skill 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 skill completely? +

Set action: deny in the PolicyLayer policy for skill. 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 skill? +

skill is provided by the Workflows MCP Server MCP server (livus-ai/skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.