InvoiceIn

Export invoice as DATEV Buchungsstapel

invoice_to_datev

Read-onlyIdempotent

Convert one received (purchase) e-invoice into a DATEV Buchungsstapel import file (EXTF format 700) for German bookkeeping in DATEV Kanzlei-Rechnungswesen or Unternehmen online. Use it only for incoming invoices booked on the German side; use invoice_to_csv for a generic table, read_invoice for the raw data, validate_invoice for rule checks (this tool does not validate). Input: XML (UBL, CII, XRechnung, Peppol BIS 3, UAE PINT AE, FatturaPA, KSeF FA(2)/FA(3)) or a ZUGFeRD/Factur-X hybrid PDF up to 25 MB; plain or scanned PDFs without embedded XML are rejected (no OCR). Returns the file content as one text string, decoded in UTF-8: the EXTF header line, the DATEV column header, then one booking row per VAT-rate group with the gross amount and S/H flag (H for credit notes), the expense account chosen by rate under the selected SKR (e.g. SKR03 3400 for 19 %, 3300 for 7 %, 3200 for 0 %, 3120 intra-EU, 3425 reverse charge), the creditor account as Gegenkonto, document and due date, invoice number in Belegfeld 1, seller name as Buchungstext and the seller VAT id on intra-EU / reverse-charge rows. Save it as UTF-8 with CRLF before importing; the account mapping is a default to confirm with the tax advisor. An unreadable file returns a tool error with the reason. Costs one invoice credit per call; without an API key the anonymous quota is 20 invoices per day per IP. Nothing is stored.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`skr`	No	German standard chart of accounts that selects the expense accounts: '03' = SKR03 (default), '04' = SKR04.	03
`path`	No	Absolute path of the invoice file on the machine running the server, used instead of file_base64. Only honoured over stdio (`python -m invoicein.mcp_server`); the hosted server at invoicein-api.peculiar.systems ignores it and answers with an error asking for file_base64.
`file_base64`	No	Invoice file content, base64-encoded (standard alphabet). Accepted content: XML in UBL 2.1, CII D16B, XRechnung, Peppol BIS Billing 3, FatturaPA 1.2 or KSeF FA(2)/FA(3) syntax, or a ZUGFeRD 1.0/2.x or Factur-X hybrid PDF (the embedded XML is used). Max 25 MB decoded. Required unless `path` is given.
`creditor_account`	No	Creditor account (Kreditor, written as Gegenkonto) the invoice is posted against: 4–9 digits as configured in the DATEV client, e.g. '70000' (default). Use the supplier's creditor number.	70000

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedSep 8, 2026

changedInput schema / properties / creditor_account / description

Previous value: -"Creditor (Gegenkonto) number to post the invoice against, e.g. 70000"New value: +"Creditor account (Kreditor, written as Gegenkonto) the invoice is posted against: 4–9 digits as configured in the DATEV client, e.g. '70000' (default). Use the supplier's creditor number."

addedInput schema / properties / creditor_account / pattern
```
Added value: +"^[0-9]{4,9}$"
```

removedInput schema / properties / file_base64 / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

changedInput schema / properties / file_base64 / default
```
Previous value: -nullNew value: +""
```

changedInput schema / properties / file_base64 / description

Previous value: -"The invoice file, base64-encoded: XML (UBL, CII, XRechnung, Peppol, FatturaPA, KSeF FA(3)) or a ZUGFeRD/Factur-X hybrid PDF. Up to 25 MB decoded."New value: +"Invoice file content, base64-encoded (standard alphabet). Accepted content: XML in UBL 2.1, CII D16B, XRechnung, Peppol BIS Billing 3, FatturaPA 1.2 or KSeF FA(2)/FA(3) syntax, or a ZUGFeRD 1.0/2.x or Factur-X hybrid PDF (the embedded XML is used). Max 25 MB decoded. Required unless `path` is given."

addedInput schema / properties / file_base64 / type
```
Added value: +"string"
```

removedInput schema / properties / path / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

changedInput schema / properties / path / default
```
Previous value: -nullNew value: +""
```

changedInput schema / properties / path / description

Previous value: -"Local file path instead of file_base64; only honoured when the server runs over stdio on the same machine."New value: +"Absolute path of the invoice file on the machine running the server, used instead of file_base64. Only honoured over stdio (`python -m invoicein.mcp_server`); the hosted server at invoicein-api.peculiar.systems ignores it and answers with an error asking for file_base64."

addedInput schema / properties / path / type
```
Added value: +"string"
```

changedInput schema / properties / skr / description

Previous value: -"German chart of accounts: '03' (SKR03) or '04' (SKR04)"New value: +"German standard chart of accounts that selects the expense accounts: '03' = SKR03 (default), '04' = SKR04."

addedInput schema / properties / skr / enum
```
Added value: +[
+  "03",
+  "04"
+]
```
removedInput schema / properties / skr / pattern
```
Removed value: -"^(03|04)$"
```

First observedSep 7, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already signal read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond that: one credit consumed per call, anonymous quota of 20 invoices per day per IP, nothing stored, unreadable files returning a tool error, and the account mapping being a default to confirm with a tax advisor. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries real operational information, from usage scope to output layout to quota limits. It is slightly redundant with the schema's file_base64 description, which already lists accepted formats and the 25 MB limit, so it is not maximally lean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with this complexity, the description is highly complete: it covers when to use it, accepted input formats, rejected inputs, output structure and encoding, post-processing requirements (UTF-8 with CRLF), error behavior, cost/quota, and privacy. An agent has enough context to call it correctly without needing the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers all parameters at 100%, so the baseline is 3. The description goes further by explaining how skr influences expense account selection with concrete examples (SKR03 3400 for 19%, 3300 for 7%, etc.) and how creditor_account maps to Gegenkonto in the output. This is useful but partly overlaps with schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Convert one received (purchase) e-invoice into a DATEV Buchungsstapel import file (EXTF format 700)'. It also clearly distinguishes the tool from siblings by naming invoice_to_csv, read_invoice, and validate_invoice and their different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly scopes usage to 'only for incoming invoices booked on the German side' and names alternatives with their conditions ('use invoice_to_csv for a generic table, read_invoice for the raw data, validate_invoice for rule checks'). It also warns that scanned PDFs are rejected and that no OCR is performed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All InvoiceIn tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.