# run_tool

A execute tool on the Uefn MCP server.

Agent View of the PolicyLayer registry record for `run_tool`. HTML page: https://policylayer.com/tools/quangdang46-uefn-verse-mcp/run-tool

## Facts

- Tool: `run_tool`
- Server: Uefn (`quangdang46/uefn-verse-mcp`) — https://policylayer.com/tools/quangdang46-uefn-verse-mcp.md
- Homepage: https://github.com/quangdang46/uefn-verse-mcp
- 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": "run_tool",
    "arguments": {}
  }
}
```

## Why run_tool is rated High

The name 'run_tool' in an MCP context that bridges to a live Unreal editor indicates code/tool execution capability. Although the description is empty (reducing confidence slightly), the function name and server purpose indicate this tool triggers external operations whose effects depend on arguments—classic Execute category behavior.

From the tool's own definition: "Tool name is 'run_tool' with empty description. In the context of a UEFN (Unreal Editor for Fortnite) MCP bridge, 'run_tool' strongly suggests execution of arbitrary tools or scripts within the editor environment."

## Use case

AI agents invoke run_tool to trigger actions in Uefn. 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 Uefn:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_tool": {
      "limits": [
        {
          "counter": "run_tool_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Uefn (142)

- `delete_actors` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/delete-actors.md
- `delete_asset` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/delete-asset.md
- `shutdown` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/shutdown.md
- `snapshot_restore` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/snapshot-restore.md
- `tag_remove` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/tag-remove.md
- `undo` — Destructive — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/undo.md
- `batch_exec` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/batch-exec.md
- `blueprint_compile` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/blueprint-compile.md
- `bulk_mirror` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/bulk-mirror.md
- `device_call_method` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/device-call-method.md
- `device_sim_generate_proxy` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/device-sim-generate-proxy.md
- `device_sim_trigger_method` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/device-sim-trigger-method.md
- `execute_python` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/execute-python.md
- `focus_selected` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/focus-selected.md
- `niagara_spawn_system` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/niagara-spawn-system.md
- `postprocess_spawn` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/postprocess-spawn.md
- `refresh_device_catalog` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/refresh-device-catalog.md
- `scatter_along_spline` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/scatter-along-spline.md
- `scatter_props` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/scatter-props.md
- `select_actors` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/select-actors.md
- `select_by_class` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/select-by-class.md
- `sign_spawn_bulk` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/sign-spawn-bulk.md
- `smart_spawn` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/smart-spawn.md
- `verse_build` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/verse-build.md
- `verse_template_deploy` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/verse-template-deploy.md
- `zone_spawn` — Execute — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/zone-spawn.md
- `bulk_randomize` — Other — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/bulk-randomize.md
- `pattern_circle` — Other — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/pattern-circle.md
- `pattern_grid` — Other — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/pattern-grid.md
- `pattern_line` — Other — https://policylayer.com/tools/quangdang46-uefn-verse-mcp/pattern-line.md
- …and 112 more: https://policylayer.com/tools/quangdang46-uefn-verse-mcp.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=quangdang46-uefn-verse-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/quangdang46-uefn-verse-mcp