Skip to main content
Glama
Sign In
Unofficial Lexware Office MCP Server

Unofficial Lexware Office MCP Server

by benethos-hub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

upload_file

Uploads a receipt file from a local path or allowed URL and creates an unchecked bookkeeping voucher, supporting PDF, JPEG, PNG, and XML files up to 5 MiB.

Instructions

Upload a receipt, which also creates a bookkeeping voucher for it.

Writes real accounting data, and the API cannot take it back: the answer carries a voucherId as well as a file id, and no call here deletes a voucher. Correcting one is a job for the web app. Confirm the organization with get_profile first. One API call, never retried.

Takes PDF, JPEG, PNG or XML, at most 5 MiB, from a path or a URL. An XML file is treated as an XRechnung. The voucher starts unchecked: update_voucher fills it in, and its finalize books it.

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": {
      "source": "<source>"
    },
    "name": "upload_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesThe file: a path on this machine, or a URL to fetch it from. A URL works only for addresses the account owner allowed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.4

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations: irreversible write ('the API cannot take it back'), no delete path for vouchers, no retry semantics, accepted formats and a 5 MiB cap, and the resulting voucher lifecycle ('starts unchecked', then update_voucher and finalize). Annotations only say non-readonly/non-idempotent; the description supplies the consequences, which is exactly the added value expected.

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-loads what it does and the irreversibility warning before the mechanics, which is the right order for a high-risk call. Dense but nearly every sentence carries distinct information; the one exception is the doubled emphasis on non-reversibility, and 'One API call, never retried' is terse to the point of being slightly cryptic.

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 one-parameter mutation with no output schema and no annotations covering consequences, it supplies everything needed: return identifiers (voucherId and file id), preconditions, size/format limits, and the follow-up workflow. Nothing material is left for the agent to guess.

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 100%, so the baseline is 3, but the description adds real constraints on the single source parameter that the schema does not: accepted formats (PDF, JPEG, PNG, XML), the 5 MiB limit, and that XML is interpreted as an XRechnung. It does not restate the path-vs-URL allowance, which the schema already covers.

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

Purpose4/5

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

Opens with a concrete verb and resource ('Upload a receipt') plus the important side effect ('also creates a bookkeeping voucher for it'), which separates it from a pure file attach. It never names the closest sibling (attach_file_to_voucher) or create_voucher, so an agent must infer that this path creates a new voucher rather than attaching to an existing one.

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?

Gives an explicit prerequisite ('Confirm the organization with get_profile first') and an explicit when-not/how-to-recover route ('Correcting one is a job for the web app'). Missing an explicit statement of when to prefer attach_file_to_voucher or create_voucher instead, which is the main sibling confusion risk.

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