The Model Context Protocol (MCP) server io.github.aarshbharat/gujarati-lexicon-mcp provides a grounded Gujarati dictionary resource intended for AI assistants. It focuses on delivering Gujarati language information, including meanings, synonyms, idioms, and inflections.
🛠️ Key Features
Grounded Gujarati dictionary content
Meanings
Synonyms
Idioms
Inflections
🚀 Use Cases
Supplying Gujarati vocabulary definitions to AI assistants
Enabling synonym and idiom lookups for Gujarati text
Supporting inflection-aware responses in Gujarati language tasks
⚡ Developer Benefits
Structured lexical coverage for Gujarati (meanings, synonyms, idioms, inflections)
Shared terminology support for AI assistant workflows using MCP context
⚠️ Limitations
Available data does not specify any particular MCP tools, capabilities, or interface behavior beyond the dictionary scope
A grounded Gujarati dictionary for AI assistants. Connect it to Claude (or any MCP client) and the assistant looks Gujarati words up in real dictionary data instead of guessing: meanings, synonyms, idioms (રૂઢિપ્રયોગ), and inflected forms like ઘરમાં or આંખોમાં.
Why this exists: LLMs are unreliable with Gujarati. They invent meanings, mix up idioms, and produce convincing but wrong usage. This server gives the model facts to stand on and tells it plainly when a word is not in the dictionary.
Demo
Example
User: અમે નો અર્થ શું છે?
Claude (after calling define): અમે means "we", the plural of હું (I)…
User: ઘરમાં નો અર્થ?
Claude: ઘરમાં = ઘર + માં → "in the house". The server matched the inflected form to its base word ઘર.
Features
Primitive
Name
What it does
Tool
define(word)
Meanings, part of speech, examples, transliteration
Tool
synonyms(word)
Synonyms (સમાનાર્થી શબ્દો) from all sources, deduplicated
Tool
idioms(word)
Idioms (રૂઢિપ્રયોગ) containing the word; never invents any
Resource
lexicon://word-of-the-day
A daily word from the hand-checked set
Prompt
explain_passage
Explains a Gujarati passage word by word using the tools
About 6,800 words with English meanings, from Wiktionary
Hand-checked entries with Gujarati meanings and idioms (curated set, growing)
Inflection handling: ઘરમાં, ઘરે, આંખોમાં, and અમે resolve to their base words
"Did you mean?" suggestions for typos (પાણિ → પાણી)
Source attribution in every response, so the assistant can say where a meaning came from
Add this to your Claude Desktop config (Settings → Developer → Edit Config):
json
"args":["gujarati-lexicon-mcp"]
Restart Claude Desktop completely (quit from the system tray), open a new chat, and ask about any Gujarati word.
On Windows, if Claude Desktop can't find uvx, use its full path (find it with where uvx), e.g. C:\\Users\\<you>\\.local\\bin\\uvx.exe.
How lookup works
A word goes through three layers, from most to least reliable:
flowchart LR
A[Input word] --> B{Exact headword?}
B -- yes --> C{Pure inflected form?}
C -- yes --> D[Follow Wiktionary link<br/>ઘરે → ઘર]
C -- no --> E[Return entry]
D --> E
B -- no --> F[Strip suffixes<br/>માં, નો, ની, ે, ો ...]
F -- match --> E
F -- no match --> G[Not found + suggestions<br/>tell the model not to guess]
Exact match. A real dictionary entry always wins over a guessed base form.
Wiktionary inflection links. Wiktionary records that ઘરે is the locative of ઘર. The converter reads the structured form_of field, and falls back to parsing glosses like "plural of X" where that field is missing.
Suffix stripping. As a last resort, common endings are removed (up to two, e.g. આંખોમાં → આંખો → આંખ). A stripped form is accepted only if it is a real headword, so words are never mangled.
Responses keep sources separate (curated vs wiktionary_senses), so the model can attribute meanings honestly.
Tatu Ylonen. Wiktextract: Wiktionary as Machine-Readable Structured Data. Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317–1325, 2022.
Rebuilding the Wiktionary data
The raw dump is not committed. To regenerate wiktionary.json:
The converter groups entries by word, keeps only what the tools need (20 MB → a compact JSON file), drops non-Gujarati-script headwords, and records inflection links.
Development
bash
git clone https://github.com/aarshbharat/gujarati-lexicon-mcp
cd gujarati-lexicon-mcp
uv sync
uv run pytest -v # run tests
uv run mcp dev src/gujarati_lexicon_mcp/server.py # open MCP Inspector
Project layout:
code
src/gujarati_lexicon_mcp/
├── server.py # MCP server: tools, resource, prompt
└── data/ # dictionary data shipped with the package
scripts/build_wiktionary.py # raw kaikki dump → wiktionary.json
tests/ # pytest
Known limitations
Verb forms are only partly covered: forms Wiktionary links (e.g. હોઈશ → હોવું) work, but phrases like લે છે are not lemmatized.
Wiktionary synonyms are merged across senses. ઘર's list includes ઓફિસ (from its "office" sense). The tool tells the model this.
The curated set is small. Most entries have English meanings only; Gujarati-language meanings and idioms come from the hand-checked data.
Grounding covers facts, not everything the model says. The model may add correct background from its own knowledge (e.g. the inclusive/exclusive "we" distinction for અમે/આપણે). The server's instructions ask it to label general knowledge, but cannot force it.
Roadmap
Grow the curated set, especially idioms and proverbs (કહેવત)
