Skip to main content
Glama
bucklo
by bucklo

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_recordsA

Search Riksarkivet's catalogue and indexed registers.

text: free text. name: person name. place: parish/place name.
year_min/year_max: restrict by year.
record_type: birth, marriage, title_deed, register, volume, record, archive (fonds),
  series, place, parish, settlement, agent. Omit for everything.
only_digitised: only material with scanned images.
limit (max 100) / offset for paging.

Note: indexed birth/marriage registers cover only some regions; use parish_archive +
get_page to read church books directly elsewhere (e.g. Östergötland).
get_register_recordA

Full details of an indexed register entry (birth, marriage, title deed) by its id from search_records - parents, occupations, residence, witnesses, volume/page.

find_placeB

Look up a place (village, farm, parish) in Riksarkivet's topographic register and show which parish/province it belongs to, including historical parishes (e.g. Harstad parish, merged into Väderstad 1891).

parish_archiveA

List the digitised volumes of a parish's church archive (kyrkoarkiv), grouped by series, with date ranges and the volume id to pass to volume_pages/get_page.

parish: e.g. "Heda", "Väderstad", "Appuna".
series: optional filter on series code or name, e.g. "C" (födelse- och dopböcker),
  "A I" (husförhörslängder), "E I" (vigsel), "F" (död), "A II" (församlingsböcker),
  "B" (flyttningslängder).

Only volumes scanned by Riksarkivet itself are listed (mostly c. 1840-1900). Lines
starting "Se:" mean the records are bound into another listed volume.
browseA

List the children of any Riksarkivet archive unit in IIIF (fonds -> series -> volumes). Use for non-church archives too (courts, military rolls, maps). archive_id is the id from search_records or parish_archive.

volume_pagesA

Show a volume's title, date range, remarks and the mapping image number -> printed page number (Bild:Sida). volume: id like 'A0006950' or a manifest URL.

get_pageA

Fetch a scanned page so it can be read. Returns the image plus a ready-made source citation (Källhänvisning) and viewer link.

volume: volume id like 'A0006950', a manifest URL, or a full image id
  like 'A0006950_00010' (then image is taken from it).
image: image number (Bild). page: printed page number (Sida) instead of image.
width: output width in px (400-3000). Use ~1600 for an overview, then zoom with region.
region: 'full', 'pct:x,y,w,h' (percent of the page) or 'x,y,w,h' pixels - e.g.
  'pct:50,0,50,50' = top-right quarter, good for reading small handwriting.
rotation: 0/90/180/270.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 7 tools

Disambiguation4/5

Most tools map to distinct steps of the archival workflow: search -> record detail -> place lookup -> archive browsing -> volume metadata -> page image. The only real overlap is parish_archive vs browse, since both list children of an archive unit, but the description explicitly scopes browse to non-church archives, which mitigates confusion.

Naming Consistency3/5

There is a partial verb_noun pattern (search_records, get_register_record, get_page, find_place, volume_pages) but it is broken by bare 'browse' and the noun-only 'parish_archive'. Readable, but conventions are mixed rather than predictable.

Tool Count5/5

Seven tools is a tight, well-scoped set that mirrors the research workflow without redundancy. Each tool earns its place, from search to image retrieval.

Completeness4/5

The surface covers the full chain of finding, inspecting and reading digitised material, plus citations. Minor gaps exist: no tool to resolve an archive/fonds-level description or to start browsing from a root archive id, and no structured export of a record's citation.

Maintenance

ActivityMaintained
ResponsivenessNo issues