Skip to main content
Glama

anglo

Server Details

Grounds LLMs in real Old English: lemmas, strong/weak paradigms, English→Old English lookup.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation4/5

Each tool has a clear core role: romanize (OE→ASCII), deromanize (ASCII→OE), search (Wiktionary lookup), and get_inflections (paradigm fetch). The only overlap is that search returns inflection tables inline while get_inflections exists to fetch them separately, but the description explicitly scopes get_inflections to cases where search left forms un-expanded, so an agent can distinguish them.

Naming Consistency4/5

All names share the anglo_ prefix and a verb/action form (romanize, deromanize, search, get_inflections). The get_ prefix on one tool versus bare verbs on the others is a minor deviation but every name reads predictably.

Tool Count4/5

Four tools is lean but each maps to a distinct operation (two transforms, one lookup, one paradigm fetch) for a narrow philological domain. It sits at the low end of the comfortable range, with no redundant or filler tools.

Completeness4/5

The romanize/deromanize pair plus search and get_inflections covers the core encode/decode/lookup/parse lifecycle, including modern-English→Old English via search_language='eng'. Minor gaps remain: no way to list or browse cached lemmas and deromanize coverage depends entirely on prior caching.

Available Tools

4 tools
anglo_deromanizeFind the Old English word(s) matching an ASCII spellingA
Read-onlyIdempotent
Inspect

Find the real Old English word(s) whose ASCII spelling matches this input — the inverse of anglo_romanize. romanize is deeply lossy (th←þ or ð, dropped macrons), so this is a LOOKUP against words already cached: attested spellings come back as source=dictionary. If none match, a single best-effort reconstruction (source=reconstruction, approximate=true) — a guess, not attested. Coverage grows as words are cached.

Inputs: text (required). Returns: The MCP-facing payload: candidates only. ``original`` is deliberately absent —…

anglo_get_inflectionsGet an Old English inflection tableA
Read-onlyIdempotent
Inspect

Fetch the full declension (nominals, including the pronouns' dual) or conjugation (verbs) table 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": } 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).

Inputs: entry_id (required), word_class (required). Returns: result

anglo_romanizeRomanize Old English to clean ASCIIA
Read-onlyIdempotent
Inspect

Reduce Old English orthography to its primary ASCII spelling (þing→thing, wæter→waeter; macrons and the dotted ġ/ċ dropped) for an ASCII-keyboard downstream. Pure local transform: no dictionary lookup, no network, always ASCII.

Inputs: text (required). Returns: The MCP-facing romanization payload: the ASCII output only. ``original`` is del…

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides LLM agents and editors read-only access to an Old English dictionary, enabling headword lookup, inflection tables, inflected-form identification, Modern English to Old English reverse lookup, and Bēowulf verse occurrences with citable URLs.
      -
    • A
      license
      A
      quality
      B
      maintenance
      Gives AI assistants grounded, sourced access to cross-linguistic data: WALS typological features and Glottolog language classifications. Answers come with provenance, family- and genus-aware counts, and clarification requests instead of guesses when codes are ambiguous.
      10
      37 PyPI
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources