Integration · Documents

Connect Claude & ChatGPT to Base64.ai

Ask your AI to pull the data out of an invoice, ID card, receipt or form with Base64.ai. It can scan a document from a link or a file, return the fields, text and document type, find signatures, and answer plain-language questions about a document it has already processed.

Connect Base64.ai free

Free plan, no credit card. Takes about a minute.

Try asking

“Scan the invoice at this link and give me the supplier, date and total.”
The AI starts a scan of the document at that public URL, then fetches the result with the extracted fields.
“What type of document is this, and what does it say?”
It scans the image or PDF you pass and returns the detected document type, fields and text right away.
“Is this contract signed?”
It checks the document for signatures and tells you what it found.

What your AI can do

Data extraction

Scan images and PDFs from a URL or as a file, and get fields, text and the detected document type for IDs, invoices, receipts, forms and more.

Signatures and questions

Find signatures in a document, and ask questions in plain language about a document that has already been processed.

Results and setup

List and read past results, and see your custom models and processing flows.

“What is the total amount on the receipt we processed this morning?”
It lists past results, finds the receipt and asks Base64.ai that question about it.
“Show me the last ten documents we processed.”
It lists recent processing results with their IDs, so you can open any of them.
“Which custom models and flows do we have?”
It lists your custom document models and your processing flows with their settings.

23 tools for Base64.ai

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

ask_about_resultChanges dataAsk questions in plain language (`questions`, a list of strings) about an already processed document by `result_uuid`, e.g. "What is the total amount?".
create_custom_modelChanges dataCreate a new custom model. API summary: Create custom model.
create_custom_model_uuidChanges dataCreate a new custom model uuid. API summary: Update custom model.
create_faceChanges dataCreate a new face. API summary: Recognize faces by file binary.
create_flowChanges dataCreate a new flow. API summary: Create Flow.
create_flow_uuidChanges dataCreate a new flow uuid. API summary: Update Flow.
create_parseChanges dataCreate a new parse. API summary: Parse a search question.
create_reportChanges dataCreate a new report. API summary: Report issues to Base64.ai Support programmatically.
create_scan_postChanges dataCreate a new scan. API summary: Mock data extraction for testing (free to use).
create_signupChanges dataCreate a new signup. API summary: Create user.
detect_signaturesChanges dataFind signatures in a document passed as `document`, a base64 data URI (e.g. data:image/png;base64,...).
get_resultGet one processing result by `result_uuid`, with the extracted fields and document type.
get_scan_statusGet the status and extracted data of a scan started with scan_document_from_url, by `async_file_uuid`.
list_custom_modelsList your custom document models.
list_flowsList your document processing flows (workflows) with their settings.
list_result_uuidsList result uuids. API summary: Get result by result uuid.
list_resultsList past document processing results with their result UUIDs.
list_usersList users. API summary: Get user data such as name, remaining credits, and tags.
scan_documentChanges dataExtract data from a document passed as `document`, a base64 data URI (e.g. data:image/jpeg;base64,...), and return the fields, text and detected document type right away.
scan_document_from_urlChanges dataStart extracting data from a document at a public `url` (image or PDF: IDs, invoices, receipts, forms and more). Returns an ID; fetch the result with get_scan_status.
search_in_flow_resultsChanges dataCreate a new flow uuid. API summary: Search in flow results.
search_in_flow_results_with_a_questionChanges dataCreate a new flow uuid. API summary: Search in flow results with a question.
update_resultChanges dataUpdate an existing result identified by result uuid. API summary: Review result.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Base64.ai from the app list.
2
Paste your key
Follow the provider setup guide to obtain these values: Login email; API key. Paste each value into its own labelled field in HeyMyApps. Use the original values; HeyMyApps handles header names, separators and any required encoding automatically.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Base64.ai?

The AI can scan documents from a URL or as a file and return fields, text and document type, find signatures, and ask questions about processed documents. It can also list and read past results and list your custom models and flows.

Does the AI see my Base64.ai credentials?

No. Your login email and API key are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, for example reading past results without starting new scans. Scans and questions can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Base64.ai account.

How do I give the AI a document?

There are two ways. Give it a public link to an image or PDF and it starts a scan, then fetches the result when it is ready. Or the document can be passed directly as a base64 data URI, and the result comes back right away.