Skip to main content
Audioscrape MCP logo
  • Category: model context protocol
  • Auth: DCR_OAUTH
  • Composio-managed OAuth available? No
  • Tools: 20
  • Triggers: 0
  • Slug: AUDIOSCRAPE_MCP
  • Version: 20261018_00

Tools

Slug: AUDIOSCRAPE_MCP_FETCHCompatibility fetch: the full transcript of a search result as one plain-text document. Clients with structured-output support should prefer get_transcript, which returns typed segments.

Input Parameters

string
required
A result id from the search tool (e.g. ep_12345)

Output

string
required
string
required
string
required
string
required
object
Slug: AUDIOSCRAPE_MCP_GET_CHARTSGet current podcast chart rankings (Apple Podcasts, Spotify) by country. Shows the top podcasts for a given market.

Input Parameters

integer
Maximum number of rankings to return
string
Country code (e.g. ‘us’, ‘gb’, ‘de’)
string ("apple" | "spotify")
Chart platform: ‘apple’ or ‘spotify’. Omit to get both platforms (each item includes a ‘platform’ field).

Output

string
string
array
required
Slug: AUDIOSCRAPE_MCP_GET_ENTITY_GRAPHExplore the knowledge graph extracted from transcribed audio. Given an entity (person, company, topic…), returns its typed relationships (employed_by, founded, supports, opposes, competes_with, invested_in, …) with quote evidence from the source audio (episode + timestamp). With second_entity, returns how two entities are connected — including co-occurrence evidence when no typed relationship exists. Relationships are machine-extracted claims with evidence, not verified facts.

Input Parameters

integer
Maximum number of relationships to return
string
required
Entity name or slug to explore (e.g. ‘Elon Musk’ or ‘elon-musk’)
string
Optional second entity name or slug. When given, returns how the two entities are connected instead of the full neighborhood.
string
Optional filter to one relationship type, e.g. ‘employed_by’, ‘founded’, ‘opposes’, ‘supports’, ‘competes_with’, ‘invested_in’.

Output

string
integer
object
required
array
required
Slug: AUDIOSCRAPE_MCP_GET_EPISODE_OVERVIEWSTART HERE for summaries and key takeaways: one small response with the episode’s chapters (titled, timestamped), speakers, most-mentioned entities, and metadata. Orders of magnitude cheaper than reading the transcript. Drill into any chapter with get_transcript(episode_id, start_time=chapter.start_time); use search_audio to find specific quotes.

Input Parameters

string
required
Episode ID (from search_audio, list_podcast_episodes, or get_transcript)

Output

string
object
required
object
array
required
array
array
integer
Slug: AUDIOSCRAPE_MCP_GET_SPEAKERGet a speaker’s bio and audio appearances (across podcasts and uploads). Use search_speakers first to find the person_slug.

Input Parameters

string
required
URL slug of the person (e.g. ‘elon-musk’)

Output

string
string
required
string
required
array
string
Slug: AUDIOSCRAPE_MCP_GET_TRANSCRIPTGet the transcript and metadata for one audio item — works for both podcast episodes and uploaded audio. For summaries/takeaways call get_episode_overview FIRST (chapters are far cheaper than reading everything). Returns speaker-identified segments with timestamps. Long episodes are paged to stay under client response limits: check the coverage object (first key in the response) — if truncated=true, call again with start_time=next_start_time until truncated=false; a truncated page means pagination, NOT missing transcription. A 3-hour episode is typically 3-5 calls.

Input Parameters

integer
Approximate response-size budget in bytes for the segment list (default 250000, max 400000). Lower it for tighter context budgets.
string
required
Episode ID to retrieve
number
Resume point in seconds — use coverage.next_start_time from the previous response to page through a long episode
boolean
Include metadata (speakers, entities)
boolean
Include full transcript segments

Output

object
required
object
object
PAGING CONTRACT (first key in the response): which part of the transcript this page covers. If truncated=true, call get_transcript again with start_time=next_start_time to continue.
object
array
required
Slug: AUDIOSCRAPE_MCP_GET_TRANSCRIPTION_STATUSCheck the status of a transcription job submitted via transcribe_audio. Returns status (‘pending’, ‘running’, ‘completed’, ‘failed’), current pipeline stage, and when complete an episode_id you can use with search_audio or get_transcript.

Input Parameters

integer
required
The job_id returned by transcribe_audio

Output

object
integer
required
string
required
integer
required
string
string
integer
string
string
string
string
integer
Slug: AUDIOSCRAPE_MCP_LIST_MY_DATASETSList the libraries (curated workspaces) the user is subscribed to, and the datasets inside each. Use this FIRST when the user asks what audio is available, what they have access to, or before scoping a search. Returns each library’s curator, role, and dataset counts (podcasts, episodes, duration).

Output

string
array
required
Slug: AUDIOSCRAPE_MCP_LIST_MY_UPLOADSList audio you have personally uploaded and transcribed (your private workspace only — does not include the public podcast corpus). Natural follow-up after transcribe_audio.

Input Parameters

integer
Maximum number of items to return
integer
Offset for pagination

Output

integer
required
array
required
Slug: AUDIOSCRAPE_MCP_LIST_PODCAST_EPISODESList episodes within one specific podcast show. Use search_podcasts first to find the podcast_id.

Input Parameters

integer
Maximum number of episodes
integer
Offset for pagination
string ("date" | "title")
Sort by: ‘date’ or ‘title’
string
required
Podcast ID to browse
Slug: AUDIOSCRAPE_MCP_LIST_RECENT_TRANSCRIPTSList recently transcribed audio (podcast episodes + your uploads) ordered by date. Use podcast_ids to scope to specific shows.

Input Parameters

integer
Maximum number of episodes
integer
Number of days to look back
array
Filter by specific podcast IDs
Slug: AUDIOSCRAPE_MCP_REQUEST_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. run curl -T <file> "<upload_url>" from where the file is), within 15 minutes. The response of that PUT contains job_id — then poll get_transcription_status. Use transcribe_audio instead when you have a direct link, a Drive/Dropbox/OneDrive share link, or the client supports file inputs (audio_file).

Input Parameters

string
Optional title for the recording.
string
The file’s name with extension (e.g. interview.m4a) so the format is known. Strongly recommended.
string
Optional description or notes about the recording.

Output

string
required
integer
required
string
required
string
required
string
required
array
Slug: AUDIOSCRAPE_MCP_SEARCHCompatibility search returning episode-level citable documents (id/title/url only). Clients with rich-result support should prefer search_audio, which returns the matching segments with timestamps, speakers, and snippets.

Input Parameters

string
required
Search query — a topic, phrase, person, or company

Output

array
required
Slug: AUDIOSCRAPE_MCP_SEARCH_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. The wider 360,000-podcast catalog is discoverable via search_podcasts but is not all transcribed; check searchable there before scoping by podcast_ids. Returns matching segments with timestamps you can cite; matches and total count SPOKEN transcript text only (episode/show metadata affects ranking, never whether something is a hit). Text mode needs the words spoken close together in one short segment — use 1-2 distinctive words, or search_type=‘semantic’ for conceptual questions. To read a whole episode, use get_transcript (paged), not repeated searches. Scope with filters.podcast_ids (ids from search_podcasts) and date filters. When the query names a known person/company/topic, entity_matches identifies it — follow up with get_entity_graph or search_entities for relationships and evidence.

Input Parameters

integer
Maximum number of results
string
required
Search query text
integer
Offset for pagination
object
Optional filters
string ("relevance" | "date" | "episode_title")
Sort results by: ‘relevance’, ‘date’, ‘episode_title’
string ("asc" | "desc")
Sort order: ‘asc’ or ‘desc’
string ("text" | "semantic")
Type of search: ‘text’ or ‘semantic’
boolean
Include surrounding segments for context

Output

integer
required
array
required
boolean
string
object
object
array
Knowledge-graph entities the query resolved to — pivot via get_entity_graph or search_entities
Slug: AUDIOSCRAPE_MCP_SEARCH_ENTITIESSearch the knowledge graph for people, companies, locations, topics, and other entities mentioned in any transcribed audio.

Input Parameters

string ("person" | "organization" | "location" | "topic" | "product")
Filter by entity type
integer
Maximum number of results
string
required
Entity name to search for
integer
Only entities mentioned in this dataset (must be a dataset you can read)

Output

integer
required
array
required
Slug: AUDIOSCRAPE_MCP_SEARCH_PODCASTSSearch the podcast catalog by title. Returns metadata including episode_count (episodes in the FEED) and searchable (whether the show has transcribed content). Results with searchable=true are listed first — only those can return hits when used with search_audio filters.podcast_ids.

Input Parameters

integer
Maximum number of results
string
required
Podcast title to search for
string
Filter by language code (e.g. ‘en’, ‘de’)

Output

integer
required
array
required
Slug: AUDIOSCRAPE_MCP_SEARCH_SPEAKERSSearch speakers and hosts by name across all transcribed audio. Returns matching people with their slug — use get_speaker for their full appearance history.

Input Parameters

integer
Maximum number of results
string
required
Person name to search for (e.g. ‘Joe Rogan’, ‘Lex’)

Output

integer
required
array
required
Slug: AUDIOSCRAPE_MCP_TRANSCRIBE_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. Give the file ONE of two ways. (1) audio_url: a direct link to the media file, or a Google Drive / Dropbox / OneDrive share link (share links are converted to direct downloads automatically — the file must be shared ‘anyone with the link’). (2) audio_file: a file the user attached in this chat, when the client supports file inputs. NEVER pass a chat-sandbox path (sandbox:/…, /mnt/data/…) or a chatgpt.com URL as audio_url — those cannot be fetched and are rejected with a hint. If the client cannot pass attachments, call request_upload_url and PUT the file bytes to the URL it returns; or ask the user for a share link. Web PAGE links (TikTok/Instagram/YouTube pages) are not files and are rejected. Returns a job_id — poll get_transcription_status. Transcription typically takes a few minutes.

Input Parameters

string
Optional title for the recording. Defaults to the filename.
string
Direct http(s) URL to the media FILE (mp3, wav, m4a, ogg, flac, aac, opus, mp4, mov, webm, mkv), or a Google Drive / Dropbox / OneDrive share link shared with ‘anyone with the link’. Not a web page. Not a sandbox:/ or /mnt/data path. Omit when passing audio_file.
object
A file the user attached in the chat (client file input). Preferred over audio_url when the user attached the audio directly.
string
Optional description or notes about the recording.

Output

object
integer
required
string
required
integer
required
string
required
integer
required
string
string