AI agents call assemblyai_transcribe to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
api_key | string | Yes | AssemblyAI API key from assemblyai.com/dashboard |
audio_url | string | Yes | Publicly accessible URL of the audio/video file |
punctuate | boolean | — | Add punctuation (default: true) |
format_text | boolean | — | Format text with capitalisation |
webhook_url | string | — | URL to POST transcript results to when complete |
summary_type | string | — | Summary format |
auto_chapters | boolean | — | Generate auto chapters |
language_code | string | — | Language code (e.g. en, es, fr, de). Omit for auto-detection. |
summarization | boolean | — | Generate a summary (also set summary_type) |
speaker_labels | boolean | — | Enable speaker diarization |
entity_detection | boolean | — | Enable named entity detection |
language_detection | boolean | — | Enable automatic language detection |
Parameters from the server's own tool schema.
Even though assemblyai_transcribe only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts URL/endpoint input (webhook_url) · Handles credentials or secrets (api_key) · High parameter count (13 properties)
Attacks that exploit this kind of access
Submit an audio or video file for transcription with AssemblyAI. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
assemblyai_transcribe accepts 12 parameters: api_key, audio_url, punctuate, format_text, webhook_url, summary_type, auto_chapters, language_code, summarization, speaker_labels, entity_detection, language_detection. Required: api_key, audio_url. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for assemblyai_transcribe: 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 UnClick. Nothing to install.
assemblyai_transcribe is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the assemblyai_transcribe 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.
Set action: deny in the PolicyLayer policy for assemblyai_transcribe. 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.
assemblyai_transcribe is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →