# Extracta.ai — how to use (mcp.ai)

Connect your Extracta.ai account and use 10 tools for document data extraction straight from your AI agent. Connect with your own API key. Extracta.ai is an AI-powered platform that automates data extraction from various document types, including PDFs, images, and text files, without requiring prior training.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_extracta_ai?ms=1787293440000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `extracta_ai_create_classification`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/extracta_ai`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/extracta_ai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/extracta_ai/create/classification` — Creates a new document classification configuration. Define a list of possible document types with their characteristics (name, description, unique words). Returns a classification ID that can be used
  - body: { classificationDetails: object }
- `POST https://api.mcp.ai/api/extracta_ai/create/extraction` — Creates a new extraction configuration for processing documents. Define what fields to extract (e.g., names, dates, amounts) and processing options. Returns an extraction ID that can be used to upload
  - body: { extractionDetails: object }
- `POST https://api.mcp.ai/api/extracta_ai/delete/classification` — Permanently deletes an entire document classification process including all associated batches, results, and uploaded files. Use this when you want to remove a classification that is no longer needed.
  - body: { classificationId: string }
- `POST https://api.mcp.ai/api/extracta_ai/delete/extraction` — Permanently deletes an extraction job and its configuration from the system. Use this when you want to remove an extraction job that is no longer needed. This action is idempotent - calling it multipl
  - body: { extractionId: string }
- `POST https://api.mcp.ai/api/extracta_ai/get/batch/results` — Retrieves extraction results for a specific batch of documents. Returns the extracted data for each file in the batch, along with processing status and file information. If the batch is still processi
  - body: { batchId: string, extractionId: string }
- `POST https://api.mcp.ai/api/extracta_ai/get/credits` — Retrieves the current credit balance available on the account. The system operates on a per-page consumption model where 1 credit = 1 page of document processing. Use this action to check remaining cr
- `POST https://api.mcp.ai/api/extracta_ai/update/classification` — Updates an existing document classification by modifying its parameters. Use this to change the classification name, description, or document types (including their keywords and linked extractions). R
  - body: { classificationId: string, classificationDetails: object }
- `POST https://api.mcp.ai/api/extracta_ai/update/extraction` — Updates an existing document extraction process by modifying specified parameters. Only fields provided in the request are modified; omitted fields remain unchanged. Use this to change the extraction'
  - body: { extractionId: string, extractionDetails: object }
- `POST https://api.mcp.ai/api/extracta_ai/view/classification` — Retrieves details of an existing classification configuration including name, description, document types, associated keywords, and linked extraction templates. Use this action to verify classificatio
  - body: { classificationId: string }
- `POST https://api.mcp.ai/api/extracta_ai/view/extraction` — Retrieves detailed configuration and status information for an existing extraction job. Returns the extraction's name, description, language, configured fields, processing options, and any associated 
  - body: { extractionId: string }

## Example prompts
- "What can I do in Extracta.ai?"
- "Show me a summary of my Extracta.ai account"

## More
- Page: https://mcp.ai/extracta_ai
- Agent spec (llms.txt): https://mcp.ai/extracta_ai/llms.txt
- Postman collection: https://mcp.ai/extracta_ai/postman.json