TollNode

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

Claude Code

List every item and price on this receipt

TollNode · Google · image-describe$0.008 · 1 image

ItemPrice (CHF)
2 x Latte Macchiato9.00
Gloki5.00
Schweinschnitzel22.00
Chässpätzli18.50
Total 54.50 CHF

Real result.

Works in Claude Code, Cursor, Codex, VS Code and any MCP agent.

What your agent gets from an image

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

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.

terminal
npx agentcash add https://tollnode.com

Copy for your AI agent

Paste this into your agent so it knows what this node does and how to call it.

prompt
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

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.

Ready in a minute

Connect your AI
For developers: endpoint, inputs and an example response

POST https://tollnode.com/api/v1/nodes/image-describe

Input

FieldTypeNotes
image*stringPublic 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)
questionstringWhat 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.