# com.valksor/latgalian

> Grounds LLMs in real Latgalian: Wiktionary lemmas, inflections, romanization.

- name: com.valksor/latgalian
- version: 2.1.0
- connection class: R0 (autonomous)
- trust: 75/100 flags: no-repository
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.valksor%2Flatgalian
- tools: https://api.protogrid.dev/v1/servers/com.valksor%2Flatgalian/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "latgalian": {
      "type": "http",
      "url": "https://latgalian.valksor.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% ~updated-105d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,875 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,875 tokens to load them all
- tool set hash: 2a929f956c66801770e56873b461a870
- tools last changed: 2026-10-13T12:39:24.135Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.valksor/latgalian.svg)](https://protogrid.dev/servers/com.valksor/latgalian)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-13 `latgalian_get_inflections` changed (inputSchema, outputSchema)
- 2026-10-13 `latgalian_search` changed (outputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.valksor%2Flatgalian/changes

## Remotes

- https://latgalian.valksor.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (4)

- `latgalian_deromanize`: Find the real Latgalian word(s) whose pronunciation-romanization matches this
clean-ASCII input — the inverse direction of `latgalian_romanize`. Because
romanize is lossy, this is a LOOKUP against the words already in the dictionary
cache: attested spellings come back as source=dictionary. If none match, a single
best-effort reconstruction is returned (source=reconstruction, approximate=true) —
a guess, not attested. Coverage grows as words are cached, so an identical query
may return a reconstruction now and a dictionary hit later.

- `latgalian_get_inflections`: Fetch the full declension (nominals) or conjugation (verbs — positive AND
negative) tables for a lemma identified by a search result's inflection
handle (entry_id + word_class). Use this only when a search ran without
inline forms or left a match un-expanded — a default search already returns
each match's table inline. Returns Markdown plus the table as
structuredContent with the shape {"result": <paradigm>} per the declared
outputSchema — switch on result.category ('nominal' | 'verbal' |
'not_found') before reading the body. Content from en.wiktionary.org
(CC BY-SA 4.0).

- `latgalian_romanize`: Strip Latgalian orthography down to clean, pronounceable ASCII for an
English-trained downstream (a voice/TTS, a search box). See the `text`
parameter doc for the exact letter mappings. Returns Markdown plus the
romanized output as structuredContent matching the declared outputSchema.
Pure local transform: no dictionary lookup, no network, and the output is
always ASCII.

- `latgalian_search`: Look a Latgalian word up on Wiktionary and return its senses plus full
declension/conjugation tables — attested content, not invented. Any form of
the word works; an inflected query is resolved to its lemma automatically
via previously cached paradigms and the result notes the resolution. With
search_language='eng' the query is an English word instead: the result
lists its per-sense Latgalian equivalents (the translations block) plus
their expanded entries. Returns Markdown plus the same result as
structuredContent matching the declared outputSchema.

Results are cached server-side; first-time queries reach the live upstream
politely and calls are rate limited — on a rate-limit error, wait a few
seconds and retry. Content is from en.wiktionary.org (CC BY-SA 4.0 —
attribute and share alike if republished).