Transkribus runs on your own machine — the client starts it, so there is no endpoint to ping. 316 installs a week from npm. Last commit 7 Nov 2026.
Transkribus REST and Processing APIs — collections, HTR/OCR; default v1, optional v2 beta.
Today is the operative word: we check Transkribus every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add transkribus -- npx -y @lazyants/transkribus-mcp-server
{
"mcpServers": {
"transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
}
[mcp_servers.transkribus]
command = "npx"
args = ["-y", "@lazyants/transkribus-mcp-server"]
{
"mcpServers": {
"transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
}
{
"servers": {
"transkribus": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
TRANSKRIBUS_USER (Account email; use with TRANSKRIBUS_PASSWORD when credentials are absent from the OS keyring), TRANSKRIBUS_PASSWORD (Account password; use with TRANSKRIBUS_USER when credentials are absent from the OS keyring), TRANSKRIBUS_SESSION_ID (Existing session ID for the legacy API; an alternative to account credentials), TRANSKRIBUS_ACCESS_TOKEN (OIDC bearer token for the Processing API; an alternative to account credentials), TRANSKRIBUS_KEYRING_SERVICE (OS keyring service containing account credentials or a legacy session ID).
31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.
Process video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.
Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.
Read-only access to comdirect accounts, transactions, depots, orders and postbox documents.
Extract data, create schemas, and export results from PDFs and documents with Suparse AI OCR.
Save schemas, preflight processing charges, extract approved documents and export owned results.
MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
Answers built from our own checks of this server.