german-archives-mcp

Overview Schema Source Related Servers Discussions Admin

nrw_search

Read-only

Search the NRW archive portal for Landesarchiv NRW civil registers and finding aids by place, Standesamt, archive department, and years; filter digitised units and get signatures and permalinks.

Instructions

Search the Archive in NRW portal, above all for the Landesarchiv NRW's civil registers.

The Rhineland's from 1798, Westphalia's and Lippe's with some church-book duplicates, within the protection periods. Each hit names the archive, signature, dates and permalink; a hit with readable_by_nrw_image is read page by page with nrw_image, by its mets. A hit is a finding aid, not the record. No hits is not a negative: registers are filed by Standesamt.

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": {
      "query": "<query>"
    },
    "name": "nrw_search"
  }
}

Input Schema

Name	Required	Description
`page`	No	Page of results, 1-based.
`rows`	No	Hits per page (1-50).
`query`	Yes	Words to find, e.g. 'Geburtsregister Barmen' or 'Sterberegister Lemgo': the register and the place or Standesamt. All words must match.
`archive`	No	One department of the Landesarchiv NRW: rheinland, westfalen, or ostwestfalen-lippe (Detmold, which keeps Westphalia's and Lippe's civil registers). Empty searches every archive in the portal.
`year_to`	No	Only units beginning by this year.
`year_from`	No	Only units reaching this year.
`has_images`	No	Only digitised units.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: it discloses result-field composition (archive, signature, dates, permalink, readable_by_nrw_image, mets), explains that protection periods suppress records, and warns that hits are finding aids rather than digitised records. The note on false negatives from Standesamt filing is genuine behavioral context an agent could not infer.

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 the core purpose, then result semantics, then the caveat about negative results — a sensible ordering. Slightly dense and the mid-sentence line breaks interrupt flow, but no sentence is filler.

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?

There is no output schema, and the description compensates by describing exactly what a hit contains and how to act on it, plus the protection-period caveat. For a seven-parameter search tool with annotations covering safety, nothing an agent needs to call it correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all seven parameters including the archive enum and year range semantics. The description reinforces query construction with concrete register-plus-place examples but adds no syntax or constraint information absent from the schema, so the baseline 3 applies.

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?

Names a specific verb and resource (search the Archive in the NRW portal) and scopes it precisely to the Landesarchiv NRW's civil registers, with regional and date coverage spelled out. It also explicitly distinguishes itself from the sibling reader tool by stating a hit is a finding aid, not the record, and that pages are read with nrw_image.

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 a clear conditional hand-off: hits carrying `readable_by_nrw_image` are read page by page with nrw_image via their `mets`. It also pre-empts misinterpretation of empty results ('No hits is not a negative: registers are filed by Standesamt'), effectively coaching query reformulation. It does not explicitly say when to prefer a different portal search tool, but the regional scoping makes that largely self-evident.

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

Deploy Server