Skip to main content
Glama
Sign In
pdfvera MCP server

pdfvera MCP server

Official
by pdfvera
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

PDF invoice to XRechnung and ZUGFeRD

convert_invoice
Idempotent

Converts German PDF invoices into XRechnung 3.0 and ZUGFeRD e-invoices, validates them against KoSIT rules, and reports missing or incorrect fields for correction.

Instructions

Convert a German PDF invoice into an e-invoice: XRechnung 3.0 (UBL and CII), a ZUGFeRD PDF (EN 16931) and a check report, checked against the KoSIT rules. Files are written next to the PDF. If mandatory data is missing, nothing is written and the result lists the missing fields with a German label, help text and example: ask the user for them (or use the offered escape value when it fits), then call again with the same PDF and answers. Wrong values read from the PDF are fixed with corrections (keys from found[].edit[].key, e.g. fix:number). Each converted invoice counts once against the monthly quota of the user's pdfvera plan; the same PDF again in the same month does not count, check_only never counts.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pdf_path": "<pdf_path>"
    },
    "name": "convert_invoice"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoWhether the user issued (issuer) or received (recipient) the invoice; only changes the wording of the questionsissuer
answersNoValues for missing fields, keyed by questions[].field, e.g. {"buyer_reference": "04011000-12345-06"}
pdf_pathYesPath of the PDF invoice on this computer
check_onlyNoOnly check, write no files and use no quota
output_dirNoFolder for the result files; default: the PDF's folder
correctionsNoCorrections of values read from the PDF, keyed by found[].edit[].key, e.g. {"fix:number": "RE-2026-0042"}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: files are written next to the PDF, a failed validation writes nothing, quota is charged once per invoice per month with the same PDF not double-counted, and check_only never counts. This reconciles the write behavior with destructiveHint=false and idempotentHint=true rather than contradicting them.

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?

Front-loaded with what is produced and where, then the failure/retry path, then quota. Every sentence carries information, though the retry instructions are compressed into a dense run-on that takes a careful read.

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 six-parameter mutating tool with nested objects and no output schema, it covers outputs, failure mode, the recovery loop, key provenance and quota economics. Nothing an agent needs to call it correctly and handle the missing-data case is absent.

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?

Schema coverage is already 100%, so the baseline is 3, but the description adds the relational meaning the schema cannot: `answers` keys come from questions[].field produced by a failed run, and `corrections` keys come from found[].edit[].key. That tells an agent how to obtain valid keys, not just their shape.

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?

Specific verb plus resource: it converts a German PDF invoice into named e-invoice outputs (XRechnung 3.0 UBL/CII, ZUGFeRD PDF EN 16931, check report). It also states the validation basis (KoSIT rules) and where files land, which makes it unmistakable next to a bank-statement converter.

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

Usage Guidelines4/5

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

It gives a clear operational flow: if mandatory data is missing, nothing is written, so ask the user and re-call with `answers`; wrong PDF-read values are fixed with `corrections`. It does not spell out when to prefer `check_only` versus a full conversion, so the alternative is only implied.

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

Deploy Server

Other Tools