# agent-run

ORCHESTRATES LIVE TOOLS. Execute an explicit discover→act→verify workflow with step IDs, result references,

Agent View of the PolicyLayer registry record for `agent-run`. HTML page: https://policylayer.com/tools/executor-mcp-roblox/agent-run

## Facts

- Tool: `agent-run`
- Server: Executor Mcp Roblox (`okenjioxx/executor-mcp-roblox`) — https://policylayer.com/tools/executor-mcp-roblox.md
- Homepage: https://github.com/okenjioxx/executor-mcp-roblox
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "agent-run",
    "arguments": {}
  }
}
```

## Why agent-run is rated High

agent-run triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke agent-run to trigger actions in Executor Mcp Roblox. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Executor Mcp Roblox:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent-run": {
      "limits": [
        {
          "counter": "agent-run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Executor Mcp Roblox (290)

- `clear-queue-on-teleport` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/clear-queue-on-teleport.md
- `clear-remote-spy-logs` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/clear-remote-spy-logs.md
- `clear-selection` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/clear-selection.md
- `clear-semantic-index` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/clear-semantic-index.md
- `delete-file` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/delete-file.md
- `delete-folder` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/delete-folder.md
- `destroy-instance` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/destroy-instance.md
- `draw-clear` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/draw-clear.md
- `draw-remove` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/draw-remove.md
- `playbook-delete` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/playbook-delete.md
- `release-closure-reference` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/release-closure-reference.md
- `remote-spy` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/remote-spy.md
- `teach-mode` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/teach-mode.md
- `vm-reset` — Destructive — https://policylayer.com/tools/executor-mcp-roblox/vm-reset.md
- `batch-execute` — Execute — https://policylayer.com/tools/executor-mcp-roblox/batch-execute.md
- `build-call-graph` — Execute — https://policylayer.com/tools/executor-mcp-roblox/build-call-graph.md
- `ensure-remote-spy` — Execute — https://policylayer.com/tools/executor-mcp-roblox/ensure-remote-spy.md
- `execute` — Execute — https://policylayer.com/tools/executor-mcp-roblox/execute.md
- `execute-and-wait` — Execute — https://policylayer.com/tools/executor-mcp-roblox/execute-and-wait.md
- `execute-file` — Execute — https://policylayer.com/tools/executor-mcp-roblox/execute-file.md
- `execute-lua-state` — Execute — https://policylayer.com/tools/executor-mcp-roblox/execute-lua-state.md
- `filter-gc` — Execute — https://policylayer.com/tools/executor-mcp-roblox/filter-gc.md
- `fire-proximity-prompt` — Execute — https://policylayer.com/tools/executor-mcp-roblox/fire-proximity-prompt.md
- `invoke-closure` — Execute — https://policylayer.com/tools/executor-mcp-roblox/invoke-closure.md
- `invoke-method` — Execute — https://policylayer.com/tools/executor-mcp-roblox/invoke-method.md
- `new-c-closure` — Execute — https://policylayer.com/tools/executor-mcp-roblox/new-c-closure.md
- `new-l-closure` — Execute — https://policylayer.com/tools/executor-mcp-roblox/new-l-closure.md
- `new-lua-state-proxy` — Execute — https://policylayer.com/tools/executor-mcp-roblox/new-lua-state-proxy.md
- `playbook-run` — Execute — https://policylayer.com/tools/executor-mcp-roblox/playbook-run.md
- `run-deferred` — Execute — https://policylayer.com/tools/executor-mcp-roblox/run-deferred.md
- …and 260 more: https://policylayer.com/tools/executor-mcp-roblox.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=executor-mcp-roblox · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/executor-mcp-roblox