# Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi

> Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi is a freemium MCP server for files and documents. Hosted MCP server giving AI clients Doxis AI.dp document capture, PDF tools. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $9 a month
- **Platforms:** API, CLI, vscode, Web
- **Website:** https://usefulapi.io/klippa-dochorizon/
- **Repository:** https://github.com/m190/usefulapi-mcp/tree/HEAD/servers/klippa-dochorizon
- **MCP Registry name:** io.usefulapi/klippa-dochorizon
- **Categories:** files and documents
- **Listing updated:** 2026-11-18

## About

The server wraps the Doxis AI.dp (Klippa DocHorizon) API so an AI client can run document extraction on invoices, receipts, IDs, bank statements and payslips without writing integration code. Each call is billed against the user's own Doxis AI.dp project credits, and the usefulapi server adds its own monthly tool-call meter on top.

Beyond capture, the 34 tools cover PDF splitting, merging and page rendering, validation and conversion of e-invoices such as EN 16931 and XRechnung files, and searches of the public Peppol directory. Long documents can be queued as asynchronous jobs, then polled and read back, and jobs can be deleted along with their stored files.

The README says the server is hosted, so there is nothing to install. Users sign in through OAuth with their own Doxis AI.dp API key and hosting region, and the server is listed as MIT licensed and unaffiliated with Doxis AI.dp. It suits finance and operations teams that already hold a Doxis AI.dp account and want to use it from Claude, ChatGPT, Cursor or VS Code.

## Features

- **Invoice and receipt capture:** Extracts merchant, dates, totals, VAT, line items and currency into structured data.
- **Identity and statement extraction:** Reads passports, bank statements and salary slips, returning personal data to the client only.
- **E-invoice validation:** Checks XML or hybrid PDF e-invoices against standards such as EN 16931 and XRechnung and lists broken rules.
- **PDF utilities:** Splits, merges and renders PDF pages, storing outputs as file IDs for reuse in other tools.
- **Asynchronous job handling:** Queues documents, reports job status and logs, and deletes jobs with their stored data.
- **Peppol directory lookup:** Searches the public Peppol directory and checks which document types a participant accepts.

## Good for

- Pull supplier, date and total fields from a batch of invoices into a spreadsheet
- Check whether a capture model returns a VAT number before building a workflow around it
- Validate outgoing e-invoices against XRechnung or EN 16931 before sending
- Split a multi-page scanned PDF into separate documents by page range
- Find which document types a supplier can receive over Peppol

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http klippa-dochorizon https://klippa-dochorizon.usefulapi.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://klippa-dochorizon.usefulapi.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "klippa-dochorizon": {
      "url": "https://klippa-dochorizon.usefulapi.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "klippa-dochorizon": {
      "type": "http",
      "url": "https://klippa-dochorizon.usefulapi.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "klippa-dochorizon": {
      "serverUrl": "https://klippa-dochorizon.usefulapi.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "klippa-dochorizon": {
      "type": "http",
      "url": "https://klippa-dochorizon.usefulapi.io/mcp"
    }
  }
}
```

## Tools

- `dochorizon_get_key_info`: Check the connected Doxis AI.dp (Klippa DocHorizon) API key: organization, project, credential id, and the services enabled for it. Does not process a document and costs nothing. GET /auth/v1/info.
- `dochorizon_list_models`: List the document capturing models enabled for this project (financial, identity, bank statement, salary slip, generic, e-invoice, ...). Does not process a document; normally not billed. GET /document_capturing/v1/enabled_models.
- `dochorizon_list_configurations`: List the capturing configurations of a model (name, slug and the enabled components). Pass a slug as configuration_slug to a capture tool to choose which fields are extracted. Does not process a document; normally not billed. GET /document_capturing/v1/{model}/configurations.
- `dochorizon_get_model_schema`: The JSON schema of what a capturing model returns (every field it can extract), optionally for one configuration. Does not process a document; normally not billed. GET /document_capturing/v1/{model}/schema or /{model}/configurations/{slug}/schema.
- `dochorizon_list_prompt_configurations`: List the Prompt Builder (LLM extraction) configurations of the project: name and slug. Does not process a document; normally not billed. GET /document_capturing/v1/prompt_builder/configurations.
- `dochorizon_get_prompt_schema`: The JSON schema of the output of one Prompt Builder configuration. Does not process a document; normally not billed. GET /document_capturing/v1/prompt_builder/configurations/{slug}/schema.
- `dochorizon_capture_financial`: SPENDS CREDITS: extract structured data from an invoice, receipt or other financial document with the Financial model: merchant and customer, dates, totals, VAT, line items, payment details, currency, and more (as the chosen configuration enables). Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost),
- `dochorizon_capture_identity`: SPENDS CREDITS: read an identity document (passport, ID card, driver's licence, visa) with the Identity model: name, date of birth, nationality, document number, expiry, MRZ, validity and fraud checks. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) c
- `dochorizon_capture_bank_statement`: SPENDS CREDITS: extract a bank statement: bank, account holder, period, opening and closing balance and every transaction. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra componen
- `dochorizon_capture_salary_slip`: SPENDS CREDITS: extract a salary slip (payslip): employer, employee, period, gross and net pay, deductions. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configu
- `dochorizon_capture_generic`: SPENDS CREDITS: turn any document into generic structured data: key-value pairs and tables, as JSON. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of u
- `dochorizon_capture_einvoice`: SPENDS CREDITS: read an invoice with the financial model and return it in the Universal Invoice structure used for e-invoicing (parties, lines, tax subtotals, totals, payment means). Does not send anything to a network. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Bil
- `dochorizon_capture_with_prompt`: SPENDS CREDITS: extract data from a document with a Prompt Builder configuration (an LLM extraction prompt you defined in the platform). Output follows that configuration's schema (see dochorizon_get_prompt_schema). The result may contain whatever personal data the document holds. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components 
- `dochorizon_submit_async_capture`: SPENDS CREDITS: queue one document for capturing and return a job_id right away; poll dochorizon_get_async_job, then read dochorizon_get_async_job_result. Use it for long documents and bursts (async jobs are not subject to the concurrent-request limit). No webhook or human review is configured. For identity, salary_slip and bank_statement the result holds personal data. Uses your own Doxis AI.dp (
- `dochorizon_list_async_jobs`: List the project's async capture jobs (newest first as returned): job_id, status, created time, with paging. Does not process a document; normally not billed. GET /document_capturing/v1/async.
- `dochorizon_get_async_job`: The status of one async capture job (in_queue, processing, hitl, done, error, closed, rejected). Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}.
- `dochorizon_get_async_job_result`: The captured data of a finished async job (status done). The result may contain personal data (identity, salary slip, bank statement). Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}/result.
- `dochorizon_get_async_job_logs`: Status changes and error messages of an async job, to debug a failed one. Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}/logs.
- `dochorizon_delete_async_job`: WRITE: permanently delete an async job, its result and the stored documents from Doxis AI.dp's servers; a job still waiting in the queue is cancelled. Use it to remove personal data you no longer need. Cannot be undone. DELETE /document_capturing/v1/async/{job_id}.
- `dochorizon_document_info`: SPENDS CREDITS: page count, page sizes, content type, metadata and permissions of a PDF or TIFF. Useful to check the page count before capturing. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free 
- `dochorizon_document_split`: SPENDS CREDITS: split a PDF into several PDFs by page ranges (one output file per range, for example ['1-3','4-6']). Output files are stored in Doxis AI.dp storage and returned as file ids you can pass to any other tool as file_id. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project'
- `dochorizon_document_render`: SPENDS CREDITS: render pages of a PDF as images, optionally limited in width/height. Each render config gives page_ranges and optional width and height in pixels. Images are stored in Doxis AI.dp storage and returned as file ids (use dochorizon_download_file for small ones). Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a c
- `dochorizon_document_merge`: SPENDS CREDITS: merge two or more PDFs into one, in the order given, optionally taking only some pages of each. The merged file is stored in Doxis AI.dp storage and returned as a file id. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform);
- `dochorizon_upload_file`: WRITE: store a file in your Doxis AI.dp storage and get a file_id to reuse in other tools (capture the same file several times without sending it again). Give a public https url or small base64 data. The file stays in your project's storage until it expires per your data-retention setting. May use credits per your pricing. POST /storage/v1/files.
- `dochorizon_download_file`: Fetch a stored file by file_id and return it as base64. Only files up to 30 KB are returned inline; for larger files use the file_id in other tools instead. Does not process a document; normally not billed. GET /storage/v1/files/{file_id}.
- `dochorizon_validate_einvoice`: Validate an e-invoice (XML or hybrid PDF) against its standard (EN 16931, XRechnung, Peppol BIS, ...): returns the detected type, valid yes/no, a summary and each broken rule with its XPath location. Nothing is sent to anyone. May use credits per your pricing. POST /einvoicing/v1/tools/validate.
- `dochorizon_convert_einvoice`: Convert an e-invoice (XML or hybrid PDF) to the Universal Invoice JSON structure (parties, lines, taxes, totals). Nothing is sent to anyone. May use credits per your pricing. POST /einvoicing/v1/tools/convert/einvoice.
- `dochorizon_list_einvoice_types`: The e-invoice types Doxis AI.dp understands (ids to pass as einvoice_type). Does not process a document; normally not billed. GET /einvoicing/v1/tools/einvoice-types.
- `dochorizon_search_peppol_directory`: Search the public Peppol business directory by company name, identifier or other text: participant identifiers, countries, contacts, websites and the document types each can receive. Public business data; costs nothing. GET /einvoicing/v1/peppol/environments/{environment}/directory.
- `dochorizon_lookup_peppol_participant`: Look up one Peppol participant by identifier (for example iso6523-actorid-upis::0106:64111512) in the Peppol network (SML): the document types it can receive. Does not process a document; normally not billed. GET /einvoicing/v1/peppol/environments/{environment}/participants/{participant_identifier}.

## FAQ

### Do I need to put an API key in my client config?

No. The README says to add only the URL; the server signs users in with OAuth and the login page asks for the Doxis AI.dp API key and hosting region.

### How many tools does the server expose?

The listing states 34 tools, 16 of which can create or change data and 14 of which are read-only.

### What does the free plan include?

The listing says the free plan gives 50 tool calls per month. Pro is $9 per month or $90 per year for 10,000 calls, and Pro+ is $39 per month or $390 per year for 100,000 calls.

### Is this an official Doxis AI.dp product?

No. The listing says usefulapi is an independent service and is not affiliated with or endorsed by Doxis AI.dp.

### Is Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi free?

Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

### How do I add Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http klippa-dochorizon https://klippa-dochorizon.usefulapi.io/mcp

### What are the best alternatives to Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi?

The closest alternatives to Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi are SSRS2, ASTra, CARTESIAN ECU, Invoices and SigPen.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 13 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [SSRS2](https://ai-powered.com/mcp/ssrs2): SSRS2 is an MCP server for files and documents.
- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [CARTESIAN ECU](https://ai-powered.com/mcp/cartesian-ecu): CARTESIAN ECU is a paid MCP server for files and documents.
- [Invoices](https://ai-powered.com/mcp/invoices): Invoices is a paid MCP server for files and documents.
- [SigPen](https://ai-powered.com/mcp/sigpen): SigPen is a freemium MCP server for files and documents.
- [ConvertAudioToText](https://ai-powered.com/mcp/convertaudiototext): ConvertAudioToText is a freemium MCP server for design and media.
- [WhoScribe](https://ai-powered.com/mcp/whoscribe): WhoScribe is a freemium MCP server for design and media.
- [filex](https://ai-powered.com/mcp/filex): filex is an open-source MCP server for files and documents.

---
Source: https://ai-powered.com/mcp/doxis-ai-dp-klippa-dochorizon-mcp-by-usefulapi
