How do I get the actual data from a document?

Use the get_document_data capability. This specifically retrieves the extracted JSON fields from documents that have a 'processed' status.

Can I use this with my existing Parseur templates?

Yes. The MCP can list your existing templates and use them to guide the extraction process for any uploaded documents.

What happens if a document fails to parse?

You can use the retry_document capability to attempt the parsing again, which is helpful after you have updated your extraction templates.

Which AI clients are compatible?

This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

Do I need to host the Parseur connection myself?

No. Vinkius hosts the MCP and manages the connection, so you only need to provide your API key to get started.

Does this capability parse the document directly or use the cloud engine?

The capability offloads the logic specifically via endpoints mapping back to the Parseur Cloud Engine. The AI acts to organize mailboxes, list templates, and fetch final states securely without computing massive local OCR networks.

Can I upload a raw file string to be parsed?

Yes. Utilizing the explicitly mapped upload_document constraint, the agent can inject raw string boundaries identifying formatting, passing files straightforward into the target mailbox ID natively.

Will I see missing required fields if extraction fails?

Absolutely. Querying get_document_details lists specific status bounds. If a template expects InvoiceTotal and misses it, the document flags a processing boundary issue precisely traceable here.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Parseur 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 unstructured PDFs and emails into clean, actionable 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 Parseur.

01
Get document details
This capability retrieves metadata for a specific parsed document. It provides context about the file without returning the actual extracted data fields.
02
Get mailbox
Use this capability to pull the configuration of a specific Parseur mailbox. It's the best way to verify your setup before you start sending documents.
03
List documents
This capability returns a list of all documents within a chosen mailbox. You'll see the document ID, the current processing status, and sender details.
04
List templates
This capability shows all the extraction templates currently active in a mailbox. These templates define the rules for how your data is pulled.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Parseur.

05
Upload document
This capability sends a document URL to a Parseur mailbox for immediate processing. It puts the file into the OCR queue and returns a new document ID.
06
Create mailbox
This capability sets up a new Parseur mailbox. You can choose the engine type, such as PDF or email, to start a new parsing pipeline.
07
Create template
This capability builds a new extraction template for a mailbox. You provide a name and a JSON configuration to map out your required fields.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Parseur.

08
Get document data
This capability pulls the fully extracted JSON data from a processed document. It's how you get the actual values like amounts or dates.
09
List mailboxes
This capability lists all your Parseur mailboxes. It's the starting point for finding the right pipeline to use for a specific task.
10
Retry document
This capability re-runs the parsing process for a document that failed or errored. It's useful after you've adjusted your template rules.

Real work

What teams actually run

Invoice Automation

Route incoming vendor invoices to a specific mailbox and have your agent extract the totals and dates automatically.

Receipt Tracking

Send receipt images to Parseur and let your agent build a structured list of expenses for your finance software.

Form Processing

Convert web contact form submissions into structured data payloads for your database.

Error Remediation

Identify documents that failed to parse and instruct your agent to retry them after you've tweaked the template.

Automate a task

Put Parseur 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

Parseur 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 Parseur 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

991ms average. Fast in production.

Parseur is checked daily against the live service.

Daily averagePeak 1084ms

Oct 11Today

Fastest day: 816ms
Slowest day: 1084ms
14-day trend: Slowing+18%

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 Parseur, so you can see the experience inside your AI.

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

Parseur Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_6MExFCZztxj2EawHbJwpL4Z4EKWcXn1vrBkxx1fJ/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 — Parseur capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "parseur-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_6MExFCZztxj2EawHbJwpL4Z4EKWcXn1vrBkxx1fJ/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 Parseur in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Parseur owners hand off.

This MCP is built for anyone who needs to turn high volumes of documents into structured data without manual entry.

01
Finance Teams
They hand off receipt and invoice processing to the agent to automate ledger updates.
02
Operations Managers
They use the agent to monitor incoming document pipelines and fix extraction errors.
03
Developers
They use the agent to test webhook bounds and automate document routing logic.

FAQ

Questions Parseur owners ask.

01
How do I get the actual data from a document?
Use the get_document_data capability. This specifically retrieves the extracted JSON fields from documents that have a 'processed' status.
02
Can I use this with my existing Parseur templates?
Yes. The MCP can list your existing templates and use them to guide the extraction process for any uploaded documents.
03
What happens if a document fails to parse?
You can use the retry_document capability to attempt the parsing again, which is helpful after you have updated your extraction templates.
04
Which AI clients are compatible?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
05
Do I need to host the Parseur connection myself?
No. Vinkius hosts the MCP and manages the connection, so you only need to provide your API key to get started.
06
Does this capability parse the document directly or use the cloud engine?
The capability offloads the logic specifically via endpoints mapping back to the Parseur Cloud Engine. The AI acts to organize mailboxes, list templates, and fetch final states securely without computing massive local OCR networks.
07
Can I upload a raw file string to be parsed?
Yes. Utilizing the explicitly mapped upload_document constraint, the agent can inject raw string boundaries identifying formatting, passing files straightforward into the target mailbox ID natively.
08
Will I see missing required fields if extraction fails?
Absolutely. Querying get_document_details lists specific status bounds. If a template expects InvoiceTotal and misses it, the document flags a processing boundary issue precisely traceable here.

Explore

More in Productivity

Connect Parseur 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

Get document details

Get mailbox

List documents

List templates

05-07

Upload document

Create mailbox

Create template

08-10

Get document data

List mailboxes

Retry document

What teams actually run

Invoice Automation

Receipt Tracking

Form Processing

Error Remediation

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

Parseur Connector

Claude Desktop

Finance Teams

Operations Managers

Developers

How do I get the actual data from a document?

Can I use this with my existing Parseur templates?

What happens if a document fails to parse?

Which AI clients are compatible?

Do I need to host the Parseur connection myself?

Does this capability parse the document directly or use the cloud engine?

Can I upload a raw file string to be parsed?

Will I see missing required fields if extraction fails?

PDF Invoice Data Extractor AI Connector

Parsio AI Connector

Docparser AI Connector

Extracta AI Connector

Suggestions

Import.io (Web Data Extraction) AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Email (.eml) File Parser AI Connector

Data Pipeline Prover AI Connector