Audioscrape MCP
for LuumenAI
Search speaker-attributed audio, pull transcripts, and share the exact moment
Audioscrape turns audio into something you can query. Ask for the episode where a vendor discussed an outage, get the transcript with speakers attributed and timestamps attached. Read chapters, entities, and speaker histories across the public podcast corpus and your own uploads. When you need to pass along a specific moment, the agent creates a share link as an approved step.
The Audioscrape MCP toolbox
20 tools: 17 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadFetchCompatibility fetch: the full transcript of a search result as one plain-text document.
- ReadGet chartsGet current podcast chart rankings (Apple Podcasts, Spotify) by country.
- ReadGet entity graphExplore the knowledge graph extracted from transcribed audio.
- ReadGet episode overviewSTART HERE for summaries and key takeaways: one small response with the episode's chapters (titled, timestamped), speakers, most-mentioned entities, and metadata.
- ReadGet speakerGet a speaker's bio and audio appearances (across podcasts and uploads).
- ReadGet transcriptGet the transcript and metadata for one audio item — works for both podcast episodes and uploaded audio.
- ReadGet transcription statusCheck the status of a transcription job submitted via transcribe_audio.
- ReadGet trendingCurrently trending people, topics, and organizations across recently transcribed audio.
- ReadList my datasetsList the libraries (curated workspaces) the user is subscribed to, and the datasets inside each.
- ReadList my uploadsList audio you have personally uploaded and transcribed (your private workspace only — does not include the public podcast corpus).
- ReadList podcast episodesList episodes within one specific podcast show.
- ReadList recent transcriptsList recently transcribed audio (podcast episodes + your uploads) ordered by date.
- ReadSearchCompatibility search returning episode-level citable documents (id/title/url only).
- ReadSearch audioSearch across all transcribed audio — ~125,000 transcribed public podcast episodes (2,300+ shows) plus your own uploaded recordings — for any topic, phrase, or speaker.
- ReadSearch entitiesSearch the knowledge graph for people, companies, locations, topics, and other entities mentioned in any transcribed audio.
- ReadSearch podcastsSearch the podcast catalog by title.
- ReadSearch speakersSearch speakers and hosts by name across all transcribed audio.
- WriteCreate share linkCreate a shareable URL for a specific audio moment that unfurls with a social-media preview card on Twitter, Slack, LinkedIn, etc. Approval by default
- WriteRequest upload urlGet a one-time URL to upload an audio/video file the user attached in this chat when it cannot be passed as a link: PUT the raw file bytes to upload_url (e.g. Approval by default
- WriteTranscribe audioTranscribe an audio or video FILE with speaker diarization; the result is indexed into the user's private workspace for search_audio and get_transcript. Approval by default
One prompt, start to finish
What a governed Audioscrape MCP run looks like inside Luumen.
Questions
Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create share link, request upload url, transcribe audio — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Audioscrape MCP — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Audioscrape MCP to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.