io.github.bepolabs/image-ocr
Image OCR Text Extractor: extract text from images
Is the Image OCR Text Extractor MCP server down? No. It is up and needs auth (HTTP 401), probed 2026-11-13.
Read printed words from receipts, forms and book pages, then export them as JSON, CSV or Excel.
needs auth probed 2026-11-14 · unchanged since 2026-11-13 · HTTP 401 · Bearer
Streamable HTTP error: Error POSTing to endpoint: {"error":"invalid_token","error_description":"Missing or invalid access token. Pass an Apify API token in the - Endpoint
- https://mcp.apify.com?tools=bepolabs/image-ocr (streamable-http)
- Host
- mcp.apify.com
- Getting access
- OAuth with dynamic client registration. A client such as Claude Code, Cursor or npx mcpcost auth https://mcp.apify.com?tools=bepolabs/image-ocr registers itself and opens the consent page; the publisher has nothing to set up for you.
Authorization server console-backend.apify.com, PKCE S256, grants authorization_code, refresh_token, urn:ietf:params:oauth:grant-type:device_code.
Scopes full_api_access.
Read from the server's public OAuth metadata, without a token. Method. - Website
- https://apify.com/bepolabs/image-ocr
- Registry
- active, updated 2026-11-12 · registry entry
Compare this server with others.
More servers
Other registry entries on mcp.apify.com, the ones next to this name; all of them.
- Google Ads Transparency Scraper: every ad of any advertiser io.github.bepolabs/google-ads-transparency · not probed
- Google Sheets Import and Export for Apify io.github.bepolabs/google-sheets · not probed
- Google Trends Scraper: keyword trends over time, per region io.github.bepolabs/google-trends · not probed
- Hacker News Scraper: stories and comments by keyword io.github.bepolabs/hacker-news · not probed
- Broken Link Checker: 404s, redirects and bad URLs io.github.bepolabs/link-checker · not probed
- Audio and Video Transcriber: Whisper text, timestamps, SRT io.github.bepolabs/media-transcriber · not probed
- NPI Registry Scraper: US doctors and providers by specialty io.github.bepolabs/npi-registry · needs auth
- npm and PyPI Package Scraper: downloads, versions, licenses io.github.bepolabs/npm-pypi · not probed
Servers that mention image.
- Aginera ai.aginera/preconstruction · needs auth
- ARPI MCP ai.arpi/arpi-mcp · no DNS
- Apatero Studio ai.apatero/studio · needs auth
- AI Media Studio ai.b77/ai-media-studio · needs auth
- Beatra ai.beatra/beatra · needs auth
- Web Search API for all your agents and LLMs ai.blopus/search · needs auth
- CCAPI ai.ccapi/mcp · alive
- CleanVector ai.cleanvector/cleanvector · alive
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers HTTP 401 to an unauthenticated initialize, so the probe cannot list its tools. That is correct for a private server. Some public servers answer initialize and tools/list without credentials and ask for auth on tool calls only; those get a token count here.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.