How do I connect Extracta to my AI client?

You subscribe to the MCP on Vinkius and provide your Extracta.ai API key. Once connected, you can use it in Claude, Cursor, Windsurf, or any compatible client.

What file types can I extract data from?

The MCP supports processing via publicly accessible URLs for PDF, JPG, and PNG files.

Can I change the fields I want to extract?

Yes. You can use the update capability to modify existing extraction settings and mapping rules without needing to create a new process.

How do I know if the extraction was accurate?

The capability provides confidence scores and predicted categories, allowing you to evaluate the reliability of the extracted data.

Do I need to wait for the extraction to finish?

The process is asynchronous. You submit the URL, and you can then poll for the results or check the status of the document ID.

Can my agent create a new data extraction setup with custom fields?

Yes. Use the 'create_extraction' capability. Provide a JSON schema defining the fields you expect (e.g., 'total_amount', 'vendor_name'). The agent will return a new extractionId for document processing.

How do I process a PDF document using a specific extraction ID via chat?

Use the 'upload_file_url' capability. Provide the extractionId and the public URL of your PDF. The agent will trigger the workflow and return a documentId, which you can use with 'get_results' to fetch the data.

Can I see the predicted document type and confidence score through the agent?

Absolutely. Use the 'get_classification_results' capability with the document and classification IDs. The agent will retrieve the AI-predicted label (e.g., 'Invoice') and the confidence score for the processed file.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Extracta to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn messy PDFs and images into clean, structured JSON data.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Extracta.

01
Upload file URL
Submits a public file URL for processing. It returns a document ID you can use to check the results later.
02
Get batch results
Retrieves a list of historical results from a specific extraction process.
03
Get classification results
Fetches the predicted category for a specific document.
04
View classification
Displays the details of an existing document classification setup.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Extracta.

05
Create extraction
Starts a new data extraction process. You define the expected fields and format, and it returns an ID to track the work.
06
Delete extraction
Removes an existing extraction process and stops any further uploads to that ID.
07
Get results
Checks the status and final JSON data for a specific document.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Extracta.

08
Update extraction
Modifies the mapping rules or settings of an active extraction process.
09
View extraction
Shows the current configuration and field settings for an extraction process.
10
Create classification
Sets up a new document classification rule. You provide a JSON schema to sort files into categories like invoices or contracts.

Real work

What teams actually run

Invoice Processing

Automatically pull vendor names and totals from a batch of invoice URLs.

Document Sorting

Use classification rules to separate contracts from receipts in a large file set.

Data Migration

Turn physical document scans into JSON payloads for database ingestion.

Audit Trails

Review historical extraction results and confidence scores to ensure data integrity.

Automate a task

Put Extracta to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Extracta works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Extracta to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

925ms average. Fast in production.

Extracta is checked daily against the live service.

Daily averagePeak 1062ms

Oct 3Today

Fastest day: 733ms
Slowest day: 1062ms
14-day trend: Slowing+21%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Extracta, so you can see the experience inside your AI.

It does not authenticate your account with Extracta. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Extracta Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_C65ttiBqS65NCFErwJyenYxrCFQRkfcwF5fUOGUO/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Extracta capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "extracta-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_C65ttiBqS65NCFErwJyenYxrCFQRkfcwF5fUOGUO/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Extracta in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Extracta owners hand off.

This MCP is built for professionals who need to turn unstructured documents into usable data without manual entry.

01
Operations Teams
They hand off invoice and receipt processing to the agent to automate data entry.
02
Data Analysts
They use the capability to convert document piles into JSON for analysis.
03
Finance Teams
They use the extraction history to audit document accuracy in real-time.
04
Developers
They use the interface to test extraction schemas and verify classification logic.

FAQ

Questions Extracta owners ask.

01
How do I connect Extracta to my AI client?
You subscribe to the MCP on Vinkius and provide your Extracta.ai API key. Once connected, you can use it in Claude, Cursor, Windsurf, or any compatible client.
02
What file types can I extract data from?
The MCP supports processing via publicly accessible URLs for PDF, JPG, and PNG files.
03
Can I change the fields I want to extract?
Yes. You can use the update capability to modify existing extraction settings and mapping rules without needing to create a new process.
04
How do I know if the extraction was accurate?
The capability provides confidence scores and predicted categories, allowing you to evaluate the reliability of the extracted data.
05
Do I need to wait for the extraction to finish?
The process is asynchronous. You submit the URL, and you can then poll for the results or check the status of the document ID.
06
Can my agent create a new data extraction setup with custom fields?
Yes. Use the 'create_extraction' capability. Provide a JSON schema defining the fields you expect (e.g., 'total_amount', 'vendor_name'). The agent will return a new extractionId for document processing.
07
How do I process a PDF document using a specific extraction ID via chat?
Use the 'upload_file_url' capability. Provide the extractionId and the public URL of your PDF. The agent will trigger the workflow and return a documentId, which you can use with 'get_results' to fetch the data.
08
Can I see the predicted document type and confidence score through the agent?
Absolutely. Use the 'get_classification_results' capability with the document and classification IDs. The agent will retrieve the AI-predicted label (e.g., 'Invoice') and the confidence score for the processed file.

Explore

More in Artificial Intelligence

Connect Extracta to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Upload file URL

Get batch results

Get classification results

View classification

05-07

Create extraction

Delete extraction

Get results

08-10

Update extraction

View extraction

Create classification

What teams actually run

Invoice Processing

Document Sorting

Data Migration

Audit Trails

Building your own app? The connector is yours to use.

Extracta Connector

Claude Desktop

Operations Teams

Data Analysts

Finance Teams

Developers

How do I connect Extracta to my AI client?

What file types can I extract data from?

Can I change the fields I want to extract?

How do I know if the extraction was accurate?

Do I need to wait for the extraction to finish?

Can my agent create a new data extraction setup with custom fields?

How do I process a PDF document using a specific extraction ID via chat?

Can I see the predicted document type and confidence score through the agent?

Parsio AI Connector

Import.io (Web Data Extraction) AI Connector

JSON5 Resilient Parser AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Suggestions

Data Pipeline Prover AI Connector

Docparser AI Connector

JSON Path Query Engine AI Connector

Alphamoon AI Connector