How does Lyro hand a document to OCR.space?

As exactly one of a file upload, a public URL, or a base64 data URI. Supplying more than one, or none, returns error E301 with OCRExitCode 99, so Lyro picks the single right form for what it has - which is why a chat attachment and a hosted image take different paths through the same integration.

Will it read a non-English or poor-quality scan?

It supports 27 languages, and for weak scans the extraction can enable orientation detection and scaling when the language is set correctly. Accuracy still depends on the source image, so Lyro works from the text that comes back and hands the conversation to a human agent when it is too unreliable to act on.

Why does Lyro report zero conversions for our account?

Get Conversion Statistics is a PRO account feature - a free API key always returns 0 conversions. The figures are also refreshed once a day and cover the start of the month through the end of yesterday, so anything processed today will not show up yet.

Can Lyro get more than a flat block of text?

Yes. The extraction supports table recognition, word-level coordinate output, and generating a searchable PDF, so a structured document does not have to collapse into one paragraph. The response is nested JSON with the text itself under ParsedResults.

Ocrspace MCP integration

Extracts text from images and PDFs, reads hosted images straight from a URL, and reports monthly conversion usage.

Connect Ocrspace See all integrations

3actions available

What your agent can do with Ocrspace

Every action runs live through MCP. Nothing to build, nothing to maintain.

Extract text from image URL (get)
Lyro extracts text from an image via URL directly without file uploads. Customers get the parsed content instantly via a streamlined GET request.
Extract text from image/PDF (ocr)
Lyro extracts text from images and PDF documents in a single call. Support handles any document type the customer submits.

See all 3 actions

How businesses use Ocrspace + Lyro

Each card is one request a support team gets, and the Ocrspace actions Lyro runs to close it.

Read a document a customer sends in
Lyro runs OCR over the receipt, invoice, or form and works from the extracted text, so a proof-of-purchase claim moves forward in the same conversation it arrived in.
Extract Text from Image/PDF (OCR)Get Conversion Statistics
Handle a scan that is crooked or not in English
With support for 27 languages plus orientation detection and scaling, Lyro can still get usable text out of a photographed page taken at an angle in another language.
Extract Text from Image/PDF (OCR)Extract Text from Image URL
Pull text from an image already hosted online
When the file lives at a public URL, Lyro uses the simplified GET endpoint rather than an upload, which is the faster path for a straightforward hosted image.
Extract Text from Image URLExtract Text from Image/PDF (OCR)
Check how much OCR the account has used
Lyro reads the conversion counts for each engine so a team can see where the month stands before pushing a large batch of documents through.
Get Conversion StatisticsExtract Text from Image/PDF (OCR)

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Ocrspace actions it has and picks the ones a request needs.

01
Connect Ocrspace
Authorize the Ocrspace account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Ocrspace actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Ocrspace · Lyro

Everything else about Ocrspace

Setup, permissions, and the limits of what Lyro can do inside Ocrspace.

As exactly one of a file upload, a public URL, or a base64 data URI. Supplying more than one, or none, returns error E301 with OCRExitCode 99, so Lyro picks the single right form for what it has - which is why a chat attachment and a hosted image take different paths through the same integration.

Every action available in Ocrspace

All 3 actions your agent can call on Ocrspace, straight from the live MCP connection.

Get conversion statistics
Retrieve OCR API conversion statistics and usage data (PRO accounts only).
Extract text from image/PDF (ocr)
Extract text from images and PDF documents using OCR (Optical Character Recognition).
Extract text from image URL (get)
Extract text from images via URL using simplified GET endpoint.