execute_skill · AGI- MCP: Risk & Policy

WHAT IT DOES

What execute_skill does on AGI-MCP

AI agents invoke execute_skill to trigger actions in AGI-MCP. 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 execute_skill needs a policy

This tool triggers execution of workflows through subagent routing and coordination. While the term 'skill' is abstract, the description makes clear it executes and orchestrates multi-step processes via specialized agents. This is Execute rather than Write because the effects are not merely data creation but active orchestration of external operations.

From the tool's definition Tool description states it will 'Execute a skill to orchestrate subagents and automate complex workflows' and 'route tasks to specialized agents.' The verb 'Execute' combined with orchestration of external agents (subagents) and multi-step process automation…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_skill Rate-limited

execute_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": {
    "execute_skill": {
      "limits": [
        {
          "counter": "execute_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 AGI-MCP, so you can run agents against it safely.

FAQ

Questions about execute_skill

What does the execute_skill tool do? +

Execute a skill to orchestrate subagents and automate complex workflows. Skills can route tasks to specialized agents and coordinate multi-step processes. It is categorised as a Execute tool in the AGI-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_skill? +

Register the AGI- MCP server in PolicyLayer and add a rule for execute_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 AGI-MCP. Nothing to install.

What risk level is execute_skill? +

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

Can I rate-limit execute_skill? +

Yes. Add a rate_limit block to the execute_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 execute_skill completely? +

Set action: deny in the PolicyLayer policy for execute_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 execute_skill? +

execute_skill is provided by the AGI- MCP server (muah1987/agi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.