Changelog

What shipped in the API, the MCP server, and the SDKs. For live uptime and response times, see status.

1. July 24, 2026MCP

   Two new MCP tools: crawl_url and get_credits

   crawl_url walks a site and returns clean Markdown per page (up to 25 pages, 1 credit each). get_credits returns your remaining balance and is free. The MCP server now exposes all eight tools the REST API supports.

   MCP docs →

2. July 24, 2026MCP

   Typed tool outputs and read-only annotations

   Every MCP tool now declares an output schema, so clients can type-check responses, plus MCP annotations marking all tools read-only and non-destructive. Added support for protocol revision 2025-11-25 and session-id headers for gateway compatibility.

3. July 23, 2026API

   GET /api/v1/me

   A free endpoint that returns your user id and current credit balance. Useful for validating a key without spending a credit, which is how the n8n node tests credentials.

   Endpoint reference →

4. July 23, 2026Integrations

   Official n8n community node

   n8n-nodes-transcriptfetch is on npm with build provenance: fetch transcripts, search and enumerate videos, and scrape or crawl pages from any n8n workflow, including as an AI Agent tool.

   View on npm →

5. July 23, 2026Billing

   Monthly credit plans

   Basic ($5 / 500 credits), Pro ($15 / 5,000) and Mega ($45 / 50,000), plus top-ups at $10 per 1,000 credits when you need more mid-month. One credit is one successful response; failures are never billed.

   Pricing →

6. July 22, 2026Docs

   A page per error code

   Every error the API can return now has its own page with the likely causes, how to fix it, and whether the request is safe to retry.

   Error reference →

7. July 21, 2026API

   Web endpoints in the playground

   Scrape a page, map a site's links, and crawl a site are all available from the dashboard playground and the request builder, alongside the transcript endpoints.

   Web docs →

8. July 19, 2026Platforms

   Transcripts beyond YouTube

   TikTok, Instagram, X, and Facebook video URLs work on the same transcript endpoint as YouTube, with AI transcription when a video has no captions. Same request shape, same response shape.

   Supported sources →

9. July 16, 2026Integrations

   Python and Node SDKs

   Official clients for both languages, so you can install a package instead of hand-rolling HTTP calls and pagination.

   SDK docs →

10. July 15, 2026MCP

    MCP server

    Connect TranscriptFetch to Claude, ChatGPT, Cursor, or any MCP client at https://transcriptfetch.com/mcp. OAuth sign-in creates an account with free credits, or pass an API key as a bearer token.

    Connect it →

Built and maintained by one developer, shipping most days. Something broken or missing? Email me and you'll get a reply from the person who wrote the code.