Latin dictionary access

An MCP server and JSON API over the English Wiktionary's Latin entries and the Morpheus analyzer — so LLMs read and write Latin with attested words and grammatical forms, not invented ones. Read-only.

MCP JSON API politely cached rate limited

Connect an MCP client

Remote streamable-HTTP endpoint — no auth, read-only: https://latin.valksor.com/mcp

Claude Code — CLI

claude mcp add --transport http latin https://latin.valksor.com/mcp

Cursor · Cline — remote url (~/.cursor/mcp.json) 

{
  "mcpServers": {
    "latin": { "url": "https://latin.valksor.com/mcp" }
  }
}

VS Code — .vscode/mcp.json 

{
  "servers": {
    "latin": { "type": "http", "url": "https://latin.valksor.com/mcp" }
  }
}

Claude Desktop · Windsurf · other stdio clients — bridge via mcp-remote (claude_desktop_config.json) 

{
  "mcpServers": {
    "latin": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://latin.valksor.com/mcp"]
    }
  }
}

Claude Desktop only accepts command-based (stdio) servers in its config, so a bare url is rejected — the bridge above wraps the remote endpoint. On Pro/Team/Enterprise you can instead add it under Settings → Connectors → Add custom connector and paste https://latin.valksor.com/mcp.

Codex CLI — ~/.codex/config.toml 

[mcp_servers.latin]
command = "npx"
args = ["-y", "mcp-remote", "https://latin.valksor.com/mcp"]

Rule of thumb: clients with native streamable-HTTP/SSE support take the url directly (Claude Code, Cursor, Cline, VS Code); stdio-only desktop apps wrap it with npx -y mcp-remote https://latin.valksor.com/mcp.

Three tools

search_latin
query — any form of the word, macrons optional.
Returns senses + inflection handles (full tables inline by default). An inflected query resolves to its lemma automatically.
get_inflections
vards_id (the lemma), word_class (the part of speech) from a handle.
Returns the full paradigm — JSON grouped by category (nominal cases or verbal voice·mood·tense), Markdown over MCP.
lemmatize_latin
word — one inflected form, e.g. amavit.
Returns Morpheus analyses: the lemma(s) plus the grammatical reading (person, number, tense, mood, voice, case).

Or call the JSON API

curl "https://latin.valksor.com/api/search?query=aqua"
curl "https://latin.valksor.com/api/inflections?vards_id=amo&word_class=verb"
curl "https://latin.valksor.com/api/lemmatize?word=amavit"

Interactive docs: /api/docs · OpenAPI schema: /api/openapi.json · LLM usage: /llms.txt

How lookup works

The dictionary is keyed by Latin headwords, but any form of a word works as a query: an inflected form is resolved to its lemma — first via paradigms already cached, then via the Morpheus analyzer — and the result says which way it was found (search_method = direct · lemma_index · morpheus). Macrons are optional: amo and amō both work.