# libi.set_mcp_server_enabled

Enable or disable an MCP server. Works on bundled and custom servers. Disabled servers are not surfaced to agents but their definition is preserved.

Agent View of the PolicyLayer registry record for `libi.set_mcp_server_enabled`. HTML page: https://policylayer.com/tools/libi/libi.set-mcp-server-enabled

## Facts

- Tool: `libi.set_mcp_server_enabled`
- Server: Libi (`Nagellabs/libi`) — https://policylayer.com/tools/libi.md
- Homepage: https://github.com/Nagellabs/libi
- Risk category: Write (Medium 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": "libi.set_mcp_server_enabled",
    "arguments": {}
  }
}
```

## Why libi.set_mcp_server_enabled is rated Medium

Toggling MCP server availability changes agent capabilities but is reversible.

From the tool's own definition: "Enable or disable an MCP server; definition is preserved"

## Use case

AI agents use libi.set_mcp_server_enabled to create or update resources in Libi, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Libi environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "libi.set_mcp_server_enabled": {
      "limits": [
        {
          "counter": "libi.set_mcp_server_enabled_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Libi (214)

- `libi.analysis_remove_step` — Destructive — https://policylayer.com/tools/libi/libi.analysis-remove-step.md
- `libi.audio_remove_clip` — Destructive — https://policylayer.com/tools/libi/libi.audio-remove-clip.md
- `libi.clear_layer_effect` — Destructive — https://policylayer.com/tools/libi/libi.clear-layer-effect.md
- `libi.delete_asset_folder` — Destructive — https://policylayer.com/tools/libi/libi.delete-asset-folder.md
- `libi.delete_caption_style` — Destructive — https://policylayer.com/tools/libi/libi.delete-caption-style.md
- `libi.delete_character` — Destructive — https://policylayer.com/tools/libi/libi.delete-character.md
- `libi.delete_clip` — Destructive — https://policylayer.com/tools/libi/libi.delete-clip.md
- `libi.delete_file` — Destructive — https://policylayer.com/tools/libi/libi.delete-file.md
- `libi.delete_folder` — Destructive — https://policylayer.com/tools/libi/libi.delete-folder.md
- `libi.delete_item` — Destructive — https://policylayer.com/tools/libi/libi.delete-item.md
- `libi.delete_keyframe` — Destructive — https://policylayer.com/tools/libi/libi.delete-keyframe.md
- `libi.delete_overlay_preset` — Destructive — https://policylayer.com/tools/libi/libi.delete-overlay-preset.md
- `libi.delete_piece` — Destructive — https://policylayer.com/tools/libi/libi.delete-piece.md
- `libi.delete_scene` — Destructive — https://policylayer.com/tools/libi/libi.delete-scene.md
- `libi.delete_track` — Destructive — https://policylayer.com/tools/libi/libi.delete-track.md
- `libi.discard_draft` — Destructive — https://policylayer.com/tools/libi/libi.discard-draft.md
- `libi.drop_proxies` — Destructive — https://policylayer.com/tools/libi/libi.drop-proxies.md
- `libi.invalidate_model_schema_cache` — Destructive — https://policylayer.com/tools/libi/libi.invalidate-model-schema-cache.md
- `libi.remove_effect` — Destructive — https://policylayer.com/tools/libi/libi.remove-effect.md
- `libi.remove_mcp_server` — Destructive — https://policylayer.com/tools/libi/libi.remove-mcp-server.md
- `libi.remove_overlay` — Destructive — https://policylayer.com/tools/libi/libi.remove-overlay.md
- `libi.remove_skill` — Destructive — https://policylayer.com/tools/libi/libi.remove-skill.md
- `libi.remove_skill_prompt` — Destructive — https://policylayer.com/tools/libi/libi.remove-skill-prompt.md
- `libi.restore_snapshot` — Destructive — https://policylayer.com/tools/libi/libi.restore-snapshot.md
- `compose_music` — Execute — https://policylayer.com/tools/libi/compose-music.md
- `isolate_audio` — Execute — https://policylayer.com/tools/libi/isolate-audio.md
- `libi.analysis_extract_audio` — Execute — https://policylayer.com/tools/libi/libi.analysis-extract-audio.md
- `libi.analysis_transcribe_audio` — Execute — https://policylayer.com/tools/libi/libi.analysis-transcribe-audio.md
- `libi.cancel_job` — Execute — https://policylayer.com/tools/libi/libi.cancel-job.md
- `libi.compute_object_track` — Execute — https://policylayer.com/tools/libi/libi.compute-object-track.md
- …and 184 more: https://policylayer.com/tools/libi.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=libi · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/libi