check_status
Check the status of a document
LABSCO SUMMARY
Start with the hosted endpoint; the local server is for offline and self-hosted setups.
The vendor now runs the server itself at https://mcp.handwritingocr.com, with OAuth instead of a copied token and a larger set of capabilities — Word, Excel and JSON export, plus field extractors. Point your client at that URL and there is nothing to install. Keep the local server for the cases the hosted one cannot serve: an air-gapped machine, or a client that cannot reach a remote MCP server at all.
What it is
An MCP server for the Handwriting OCR service. You upload an image or a PDF, poll its status while the service works, and retrieve the transcription as Markdown — the three steps that a handwriting job actually takes, since transcription is not instantaneous.
What you get
- An image or PDF document submitted for transcription
- The status of a submitted document checked while it is processing
- The finished transcription retrieved as Markdown, ready to paste or edit
- A hosted endpoint at
https://mcp.handwritingocr.comwith a wider surface than the local server: the same submit, status and retrieve cycle plus export to Word, Excel or JSON, and extractors that pull named fields out of a form rather than transcribing it whole
Requirements
A Handwriting OCR account. For the hosted endpoint that is all: authorization runs over OAuth in your browser, with no token to copy. For the local server you also need an API token from the platform's API settings, supplied as API_TOKEN, and Node.js 18.x or higher. The npm package name is handwriting-ocr (0.1.0) and it is marked private, so build from a clone or use the Smithery installer. Stdio-only clients can still reach the hosted endpoint by bridging through mcp-remote.
Setup effort
One command plus a key — npx -y @smithery/cli install @Handwriting-OCR/handwriting-ocr-mcp-server --client claude, then supply credentials
USE CASES
01
Reading a handwritten document you cannot type out
Upload the scan, wait for the job to finish, and get the text back as Markdown you can edit rather than an image you cannot search.
02
Digitising a stack of archive pages
Submit each PDF, poll the statuses, and collect the transcriptions as they complete instead of waiting on each one in turn.
03
Pulling named fields out of completed forms
Use the hosted endpoint's extractors to get structured values — dates, names, amounts — rather than a page of prose you then have to parse.
04
Getting a transcription into a document someone else can use
Export the result to Word, Excel or JSON from the hosted endpoint, rather than copying Markdown into a file by hand.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
get_text
Retrieve the transcribed text from a document
upload_document
Upload a document to Handwriting OCR API for transcription
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected.
CONTEXT COST
Light Standing cost
Rated by the size of the 3 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
npx
TERMINAL
npx -y @smithery/cli install @Handwriting-OCR/handwriting-ocr-mcp-server --client claudeHosted endpoint
ENDPOINT URL
https://mcp.handwritingocr.comAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
