assemblyai-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ASSEMBLYAI_API_KEY | Yes | Your AssemblyAI API key. Keys come from the dashboard at https://www.assemblyai.com/dashboard |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| upload_fileA | Upload a local audio or video file and get a URL that transcribe accepts. |
| transcribeB | Transcribe an audio or video file from a URL. Waits for the result by default. |
| get_transcriptA | Fetch a transcript by id, including its status if it is still running. |
| list_transcriptsB | List recent transcripts on the account. |
| get_subtitlesA | Get SRT or VTT subtitles for a completed transcript. |
| search_transcriptA | Find where words are spoken in a transcript. Returns counts and timestamps. |
| get_speaker_turnsB | Get who said what, for a transcript made with speaker_labels. |
| ask_transcriptC | Ask a question answered from one or more transcripts. |
| summarize_transcriptC | Summarise one or more transcripts. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct part of the transcription workflow: upload, transcribe, retrieve, list, subtitles, search, speaker turns, Q&A, and summarization. Even the two transcript-based text tools, ask_transcript and summarize_transcript, are clearly separated by their descriptions.
Almost all tools follow a clear verb_noun pattern (upload_file, get_transcript, list_transcripts, ask_transcript). The only minor deviation is 'transcribe', which is a bare verb without an explicit object, but it remains predictable given the server's purpose.
Nine tools is a well-scoped set for a transcription-focused MCP server. Each tool earns its place, covering the main AssemblyAI features without unnecessary duplication or bloat.
The set covers the core lifecycle well: upload, transcribe, retrieve, list, subtitles, and several post-processing features. The main gap is the absence of a delete_transcript tool, which prevents full CRUD coverage, but agents can still complete typical transcription workflows.