# csv2zugferd (nuget · csv2zugferd)

csv2zugferd setup assistant: drafts and checks the CSV to ZUGFeRD/Factur-X mapping, local via stdio

- Trust score: 72/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- nuget · `csv2zugferd`: 72/100 (this document), [markdown](https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd.md), [page](https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd)

## Channel facts

- Registry: `nuget`
- Package: `csv2zugferd`
- Version: `1.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Build provenance not yet verified.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1399 tokens (~174/item across 8 items; 5 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the csv2zugferd MCP server?

csv2zugferd runs locally as a NuGet package, launched with dnx csv2zugferd@1.3.1 --yes -- mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add de-zugferd-tools-csv2zugferd -- dnx csv2zugferd@1.3.1 --yes -- mcp
```

### Cursor

```json
{
  "mcpServers": {
    "de-zugferd-tools-csv2zugferd": {
      "command": "dnx",
      "args": [
        "csv2zugferd@1.3.1",
        "--yes",
        "--",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "de-zugferd-tools-csv2zugferd": {
      "command": "dnx",
      "args": [
        "csv2zugferd@1.3.1",
        "--yes",
        "--",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add de-zugferd-tools-csv2zugferd -- dnx csv2zugferd@1.3.1 --yes -- mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "de-zugferd-tools-csv2zugferd": {
      "type": "local",
      "command": [
        "dnx",
        "csv2zugferd@1.3.1",
        "--yes",
        "--",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  de-zugferd-tools-csv2zugferd:
    command: "dnx"
    args: ["csv2zugferd@1.3.1", "--yes", "--", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "de-zugferd-tools-csv2zugferd": {
      "Transport": "stdio",
      "Command": "dnx",
      "Arguments": [
        "csv2zugferd@1.3.1",
        "--yes",
        "--",
        "mcp"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "de-zugferd-tools-csv2zugferd": {
      "command": "dnx",
      "args": [
        "csv2zugferd@1.3.1",
        "--yes",
        "--",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-09 (score 72, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-08 (score 57)

First indexed and scored.

## MCP tools (5)

### `csv2zugferd_config_file_create` (~210 tokens)

Save configuration file

Validates configYaml (it must deserialize as a csv2zugferd configuration) and writes it to configPath as UTF-8 without BOM. An existing file is replaced only with overwrite: true; otherwise the call is rejected with file_exists and nothing is written. Returns the full path, the size and the csv2zugferd CLI command that uses the saved file for production runs. Does not run the mapping (use csv2zugferd_invoice_get first) and does not create XML or PDF files.

Input parameters:

- `configPath` (string, required): Target file path, for example C:/invoices/config.yml. The directory must exist.
- `configYaml` (string, required): The YAML configuration to save (content of the file).
- `csvPath` (string): Optional CSV path inserted into the returned CLI command instead of a placeholder.
- `overwrite` (boolean): True replaces an existing file at configPath. Default false: an existing file is never touched (file_exists).

Output parameters:

- `bytes` (integer): Size of the written file in bytes (UTF-8 without BOM).
- `cliCommand` (string): Complete csv2zugferd CLI command for a production run with this configuration; placeholders in angle brackets mark paths that were not given.
- `configPath` (string): Full path of the written file.

### `csv2zugferd_config_get` (~198 tokens)

Check configuration

Loads a YAML configuration from configPath or configYaml and reports its structure: effective settings and modes, every mapped field with its sources, unknown keys (typos), values outside the allowed sets with the fallback the CLI would apply, and ignored or missing sections. With csvPath the referenced columns are compared with the CSV header (missing and unused columns). Does not read cell values and does not calculate totals; use csv2zugferd_invoice_get for a trial run. Read-only, writes no files.

Input parameters:

- `configPath` (string): Path to an existing YAML configuration file. Use either configPath or configYaml, not both.
- `configYaml` (string): YAML configuration as text (the content of config.yml). Use either configPath or configYaml, not both.
- `csvPath` (string): Optional CSV file whose header is compared with the referenced columns (structural check, no cell values are read).

Output parameters:

- `columnsMissing` (array): Only with csvPath: referenced columns without any match in the header (case-insensitive), neither direct nor indexed.
- `columnsReferenced` (array): CSV column names the configuration can read in the effective mode (direct names; in columns mode also the indexed names built from columnPattern).
- `columnsUnused` (array): Only with csvPath: header columns no mapping refers to.
- `csv` (object): Effective CSV settings.
- `invalidValues` (array): Configured values outside their value set (version, profile, format, modes, currency, country, unit code, tax codes, type codes, schemes).
- `lineItemsMode` (string): Effective line item mode after fallback.
- `mappedFields` (array): Every configured field mapping with its configured sources in resolution order.
- `source` (string): Where the configuration came from.
- `totalsMode` (string): Effective totals mode after fallback.
- `unknownKeys` (array): Keys in the YAML that no configuration key matches (typos); they are silently ignored by the CLI.
- `warnings` (array): Structural findings: ignored or missing sections for the chosen modes, fallbacks of version, profile and format.
- `zugferd` (object): Effective output settings after fallbacks (canonical spelling).

### `csv2zugferd_config_schema_get` (~168 tokens)

Get configuration reference

Returns the reference of the csv2zugferd YAML configuration: a JSON Schema of every key with description, type, default and allowed values, plus semantics per key (effect, mode dependency, resolution order value > column > rules > default, fallback for unknown values). Use it before drafting a configuration; no README is needed. The complete reference is about 100 KB; pass section (for example mapping.lineItems) to get one subtree with its definitions. Does not check a concrete configuration (use csv2zugferd_config_get). Read-only.

Input parameters:

- `section` (string): Optional configuration path to return only that subtree with the definitions it uses, for example zugferd, mapping.lineItems or mapping.paymentMeans. Semantics are filtered to the same subtree.

Output parameters:

- `schema`: JSON Schema (Draft 2020-12) of the whole YAML configuration (or of the section) with descriptions, defaults and value sets; $defs holds the shared definitions used.
- `schemaVersion` (string): csv2zugferd version the schema was generated from.
- `section` (string|null): The section argument as given, or null for the complete reference.
- `semantics` (array): Effect, modes, resolution sources and value sets per configuration path (filtered to the section when given).

### `csv2zugferd_csv_header_get` (~227 tokens)

Read CSV header

Reads the header row of a CSV file and returns the column names in file order plus the number of data rows. Optionally returns up to 3 sample rows (sampleRows, default 0) so the mapping can be drafted from real values. Does not validate a configuration (use csv2zugferd_config_get) and does not map an invoice (use csv2zugferd_invoice_get). Read-only, writes no files.

Input parameters:

- `csvPath` (string, required): Path to the CSV file on the local file system (absolute or relative to the server's working directory).
- `encoding` (string): Text encoding of the file, for example UTF-8 or windows-1252. Same meaning as csv.encoding in the YAML configuration.
- `sampleRows` (integer): Number of data rows to return as samples, 0 to 3. Default 0 returns no cell values, only the header.
- `separator` (string): Column separator used in the file. Use "\t" for tab. Same meaning as csv.separator in the YAML configuration.

Output parameters:

- `columnCount` (integer): Number of columns in the header row.
- `columns` (array): Column names from the header row in file order.
- `csvPath` (string): The csvPath argument as given.
- `encoding` (string): The encoding that was applied.
- `rowCount` (integer): Number of data rows after the header.
- `sampleRows` (array): Sample data rows, each as a list of cell values in column order. Empty unless sampleRows > 0.
- `separator` (string): The separator that was applied.

### `csv2zugferd_invoice_get` (~352 tokens)

Trial run invoice mapping

Runs the real csv2zugferd mapping for one CSV file with the given configuration (configPath or configYaml) without writing any output file: reads the CSV, maps header, parties, line items and totals, builds the ZUGFeRD XML in memory and returns invoice number, type, totals, tax breakdown, warnings with codes and paths, and the XML size. includeLineItems and includeParties (default false) add details; pdfTemplatePath also embeds the XML into a temporary PDF copy to check format and template. Does not create the XML or PDF for production; that is done by the csv2zugferd CLI (csv2zugferd_config_file_create returns the command). Read-only for the user's files; a temporary PDF is created and deleted only with pdfTemplatePath.

Input parameters:

- `configPath` (string): Path to an existing YAML configuration file. Use either configPath or configYaml, not both.
- `configYaml` (string): YAML configuration as text (the content of config.yml). Use either configPath or configYaml, not both.
- `csvPath` (string, required): Path to the CSV file with the invoice data.
- `includeLineItems` (boolean): True adds the mapped line items (name, quantity, unit, price, line total, tax rate) to the result.
- `includeParties` (boolean): True adds seller and buyer (name, city, country) to the result.
- `pdfTemplatePath` (string): Optional PDF template: the trial run also embeds the XML into a copy of this PDF in the temp directory (deleted afterwards) and reports its size, which checks zugferd.format and the template.

Output parameters:

- `currency` (string): Currency code (BT-5).
- `format` (string): Effective XML syntax (applied in the PDF only).
- `invoiceDate` (string): Invoice date (BT-2) as yyyy-MM-dd; 0001-01-01 when the date could not be parsed.
- `invoiceNumber` (string): Invoice number (BT-1) as mapped.
- `lineItemCount` (integer): Line items in the invoice.
- `lineItems` (array): Mapped line items; only with includeLineItems.
- `parties` (object): Seller and buyer; only with includeParties.
- `pdfBytes` (integer): Size of the generated PDF in bytes; only with pdfTemplatePath.
- `profile` (string): Effective ZUGFeRD profile as library name; a configured EN16931 is reported as Comfort (same profile).
- `rowCount` (integer): Data rows read from the CSV.
- `taxBreakdown` (array): VAT breakdown per rate and category (BG-23).
- `totals` (object): Document totals (BG-22).
- `typeCode` (string): Invoice type code (BT-3), for example 380.
- `version` (string): Effective ZUGFeRD version.
- `warnings` (array): All findings of the run: document checks, fallbacks, unparsable values, ignored or missing sections.
- `xmlBytes` (integer): Size of the generated XML in bytes.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd#diagnostics

## Score history

- 2026-11-21: 72
- 2026-11-20: 72
- 2026-11-19: 72
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 72
- 2026-11-12: 72
- 2026-11-11: 72
- 2026-11-10: 72
- 2026-11-09: 72
- 2026-11-08: 57

## Common questions

### What is the csv2zugferd MCP server?

csv2zugferd is an MCP server listed in the public MCP registry as de.zugferd-tools/csv2zugferd. csv2zugferd setup assistant: drafts and checks the CSV to ZUGFeRD/Factur-X mapping, local via stdio. This page covers its NuGet package (csv2zugferd).

### Is the csv2zugferd MCP server safe to use?

csv2zugferd scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the csv2zugferd MCP server expose?

csv2zugferd exposes 5 tools: csv2zugferd_config_file_create, csv2zugferd_config_get, csv2zugferd_config_schema_get, csv2zugferd_csv_header_get, csv2zugferd_invoice_get. Their descriptions and schemas cost roughly 1,155 tokens of context every time the server is loaded.

### Is the csv2zugferd MCP server still maintained?

csv2zugferd is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the csv2zugferd MCP server under?

csv2zugferd declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the csv2zugferd MCP server?

VerifyMCP ran 14 checks on csv2zugferd, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about csv2zugferd: Provenance and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a NuGet package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- NuGet package: https://www.nuget.org/packages/csv2zugferd
- Socket report: https://socket.dev/nuget/package/csv2zugferd
- Repository: https://github.com/rillsoft/csv2zugferd
- Website: https://zugferd-tools.de/docs/mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd.xml
- Changelog JSON feed: https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd.json
- HTML version of this page: https://verifymcp.io/servers/de-zugferd-tools-csv2zugferd/csv2zugferd
