Image description and OCR API and MCP for agents
TollNode gives Claude, Cursor or any AI agent a description of any image, the text in it (receipts, screenshots, signs) or an answer to your question about it, from $0.008 per image.
Ask in plain words, like 'list every item and price on this receipt', and get the lines back as text.
No subscription · Sign-up optional · From $0.008 per call · Charged only when it works · No Google account needed
List every item and price on this receipt
TollNode · Google · image-describe$0.008 · 1 image
| Item | Price (CHF) |
|---|---|
| 2 x Latte Macchiato | 9.00 |
| Gloki | 5.00 |
| Schweinschnitzel | 22.00 |
| Chässpätzli | 18.50 |
| Total 54.50 CHF | |
Real result.
What your agent gets from an image
Read the text
Image OCR and description API
Receipts, screenshots, signs and documents.
- Image
- photo of a receipt
- Question
- List every item and price on this receipt
- Answer
- 2 x Latte Macchiato: 9.00 CHF...
You get
- answer: the text, as plain text
- question: what you want to know
- image: public link to a jpg, png or webp, up to 7 MB
- default: describe the image
- language: text in many languages
Describe and answer
What is in the picture, or a specific question.
- Image
- a ceramic mug on a wooden table
- Question
- Describe this image and copy any text in it.
- Answer
- A ceramic mug on a wooden table with the words ...
You get
- description: what is in the image
- question: ask anything about it
- answer: returned as plain text
- size: up to 7 MB
- formats: jpg, png or webp
Every result is structured JSON your agent can sort, filter, summarize or turn into a spreadsheet.
What people ask their AI to do with it
Finance teams
Capture receipts
“Read this receipt and list the items and total”
1 call
Cost today$0.008
Support teams
Read customer screenshots
“What error message is shown in this screenshot?”
1 call
Cost today$0.008
Ecommerce sellers
Write alt text
“Describe this product photo in one sentence for alt text”
3 calls
Cost today$0.024
Operations teams
Digitize signs and labels
“Copy the text from this shelf label”
1 call
Cost today$0.008
Accessibility teams
Describe images for screen readers
“Describe this chart in plain words”
1 call
Cost today$0.008
Researchers
Extract from figures
“Read the numbers in this chart image”
1 call
Cost today$0.008
Use it as a Image description and OCR MCP server in Claude, Cursor or Codex
Connect once. Then just ask.
Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.
npx agentcash add https://tollnode.comCopy for your AI agent
Paste this into your agent so it knows what this node does and how to call it.
You can use TollNode's Image description and OCR node. Call POST https://tollnode.com/api/v1/nodes/image-describe with image (required), question (optional). The price is one flat price per call, charged only when it returns a result. Over MCP, call the "image-describe" tool; use list_models to see prices. Return results as tables when I ask for lists.Price
$0.008
per image
Charged only when a call returns a result. Failed or empty calls cost $0.
Image description and OCR data without a scraper
No subscription, no credit packs
Pay per image: $0.008 for every call, with nothing to choose.
No Google account, no vision API key, no billing project
Your agent calls TollNode. You never set up billing or request access with anyone else.
Only charged when it works
If a call returns nothing or fails, it costs nothing.
One connection, much more
The same setup also gives your agent Google search, YouTube, Maps, images and video, so one prompt can chain them.
FAQ
- Is this the official Google API?
- No. TollNode is an independent service. It gives your agent image description and text reading through its own API and MCP server, priced per image.
- Can I use it as a Image description and OCR MCP server in Claude?
- Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "image-describe" tool appears with its fields and price.
- What files work?
- A public https link to a jpg, png or webp image, up to 7 MB.
- What do I ask?
- Anything about the image, such as 'List every item and price on this receipt'. Without a question it describes the image.
- Does it return text only?
- Yes. The answer comes back as plain text.
- Do I need a Google account?
- No. Your agent calls TollNode, and you never log in to Google or share cookies.
- What if nothing comes back?
- You're not charged. TollNode only collects payment when a usable result is returned, and your agent can try a different input.
Works well with
Ready in a minute
Connect your AIFor developers: endpoint, inputs and an example response
POST https://tollnode.com/api/v1/nodes/image-describe
Input
| Field | Type | Notes |
|---|---|---|
| image* | string | Public URL of the image (jpg, png or webp, up to 7 MB). Or send the file inline as a base64 data: URI (up to 4.5 MB) |
| question | string | What you want to know, e.g. 'List every item and price on this receipt'. Default: describe it and copy its text |
Example response
{
"answer": "A ceramic mug on a wooden table with the words …"
}Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.