Skip to main content
Glama
Sign In
matricula-mcp

matricula-mcp

by ianderso
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

matricula_registers

Read-only

List a parish's registers with signatures, dates, notes, and keys, and filter by baptism, marriage, burial, or other record kinds for genealogical research.

Instructions

List a parish's registers: signature, type, dates, notes, and each one's key.

type is the archive's own word (Taufen, Trauungen, Sterben, Index - ...); kind is this server's reading of it. Page counts and page links come from matricula_register. A register with hosted_elsewhere is shown on the archive's own site, not in Matricula's viewer. A gap in the years may be a register closed by law, unscanned, or lost.

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": {
      "parish": "<parish>"
    },
    "name": "matricula_registers"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoKeep registers of this kind (indexes included).any
parishYesA parish key, e.g. 'oesterreich/salzburg/krimml', or its Matricula address.
refreshNoTrue asks Matricula again instead of using the cache, and replaces the cached copy. Lists are kept 28 days, parish and register pages 7, searches 1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real domain context beyond them: `type` is the archive's own label while `kind` is the server's interpretation, `hosted_elsewhere` means the register lives on the archive's site rather than the Matricula viewer, and a year gap may mean a legally closed, unscanned, or lost register. It does not restate the cache/replacement behavior, but that is covered by the `refresh` parameter description.

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 purpose is front-loaded in the first sentence, and the remaining lines each carry distinct information (type vs kind, hosted_elsewhere, year gaps). It is dense but not padded; the backticked field references make it readable, though the multi-line formatting is slightly heavier than needed.

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?

With no output schema available, the description takes on the burden of describing return values and does so by naming the fields (signature, type, dates, notes, key) and flagging the `hosted_elsewhere` case that changes what the agent can do next. Combined with fully documented parameters, an agent has what it needs to call this correctly and interpret the result.

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 genuinely adds meaning for the enum parameter: it explains that `kind` is the server's own reading of the archive's `type`, which is exactly the ambiguity an agent would otherwise hit when choosing a `kind` value. `parish` and `refresh` are left to the schema, which is fine given their quality.

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 opening sentence names a specific verb (List) and resource (a parish's registers) and enumerates the fields returned: signature, type, dates, notes, and each one's key. It also draws a boundary against the sibling by noting that page counts and page links come from matricula_register, so an agent can distinguish the two without opening a schema.

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 tells the agent when this tool is the right one (listing a parish's registers) and explicitly routes the page-level follow-up to matricula_register. What's missing is an explicit 'do not use this for X' exclusion or guidance on getting a parish key first, so usage is clear but not fully closed.

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