# transcribe_url

RECOMMENDED for Open CLAW agents.

Agent View of the PolicyLayer registry record for `transcribe_url`. HTML page: https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/transcribe-url

## Facts

- Tool: `transcribe_url`
- Server: Open CLAW Knowledge Distiller (`destinyfrancis/openclaw-knowledge-distiller`) — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller.md
- Homepage: https://github.com/destinyfrancis/openclaw-knowledge-distiller
- Risk category: Execute (High risk)
- Registry record: grade B, 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": "transcribe_url",
    "arguments": {}
  }
}
```

## Why transcribe_url is rated High

This tool executes a transcription pipeline (local transcription or subtitle extraction plus AI summarization) against a provided URL. It is not a simple read/query — it triggers computation and potentially external network requests. No data destruction or financial action is involved. The closest category is Execute, as it runs a processing workflow whose effects depend on the input URL.

From the tool's own definition: "Tool name 'transcribe_url' and server description mentions 'local transcription or subtitle extraction combined with AI-powered summarization' — triggers an external/local processing operation on a given URL"

## Use case

AI agents invoke transcribe_url to trigger actions in Open CLAW Knowledge Distiller. 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 Open CLAW Knowledge Distiller:

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

## Other tools on Open CLAW Knowledge Distiller (6)

- `process_url` — Execute — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/process-url.md
- `get_result` — Read — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/get-result.md
- `get_status` — Read — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/get-status.md
- `list_jobs` — Read — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/list-jobs.md
- `list_styles` — Read — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/list-styles.md
- `configure` — Write — https://policylayer.com/tools/destinyfrancis-openclaw-knowledge-distiller/configure.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=destinyfrancis-openclaw-knowledge-distiller · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/destinyfrancis-openclaw-knowledge-distiller