Gujarati Lexicon Mcp

io.github.aarshbharatv0.2.1Updated Oct 8, 2026

Grounded Gujarati dictionary for AI assistants: meanings, synonyms, idioms, inflections

VerifiedSTDIODesktop onlyKnowledge & Memory

Overview

AI-generated overview

Lets an assistant look up Gujarati words in real dictionary data for meanings, synonyms, idioms, and inflected forms.

What it does
Provides a grounded Gujarati dictionary so the assistant looks words up instead of guessing. Tools include define(word) for meanings, part of speech, examples and transliteration; synonyms(word) for deduplicated synonyms; and idioms(word) for idioms containing the word. It also exposes a word-of-the-day resource and an explain_passage prompt that explains a Gujarati passage word by word. Inflected forms such as ઘરમાં resolve to their base words, and responses include source attribution.
When to use it
Useful when working with Gujarati text and needing reliable meanings, synonyms, or idioms rather than model guesses. Also helpful for explaining Gujarati passages word by word or checking whether a word is actually in the dictionary.
Requirements
Runs locally as a stdio process, installed from the PyPI package gujarati-lexicon-mcp. Requires uv. Needs an API key supplied through the environment variable YOUR_API_KEY. Desktop only; not available as a web executable.
Before you install
The server requires a secret API key via the environment variable YOUR_API_KEY. Dictionary data comes from Wiktionary (CC BY-SA) and a curated set; the curated set is small and verb forms are only partly covered, so some lookups may be incomplete.

Installation

In SourceWeft

  1. Open Gujarati Lexicon Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Gujarati Lexicon MCP Server [PyPI]

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

PrimitiveNameWhat it does
Tooldefine(word)Meanings, part of speech, examples, transliteration
Toolsynonyms(word)Synonyms (સમાનાર્થી શબ્દો) from all sources, deduplicated
Toolidioms(word)Idioms (રૂઢિપ્રયોગ) containing the word; never invents any
Resourcelexicon://word-of-the-dayA daily word from the hand-checked set
Promptexplain_passageExplains 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

Quick start

Requires uv.

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:

mermaid
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]
  1. Exact match. A real dictionary entry always wins over a guessed base form.
  2. 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.
  3. 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.

Data sources

SourceProvidesLicense
curated.jsonGujarati meanings, idioms, synonyms (hand-checked)MIT (this project)
wiktionary.json~6,800 words: English meanings, transliterations, synonyms, inflection linksCC BY-SA

Wiktionary data comes from Wiktionary via kaikki.org, extracted with wiktextract:

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:

bash
mkdir -p data/rawcurl -L -o data/raw/kaikki-gujarati.jsonl "https://kaikki.org/dictionary/Gujarati/kaikki.org-dictionary-Gujarati.jsonl"uv run python scripts/build_wiktionary.py

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-mcpcd gujarati-lexicon-mcpuv syncuv run pytest -v                                    # run testsuv run mcp dev src/gujarati_lexicon_mcp/server.py   # open MCP Inspector

Project layout:

src/gujarati_lexicon_mcp/├── server.py           # MCP server: tools, resource, prompt└── data/               # dictionary data shipped with the packagescripts/build_wiktionary.py   # raw kaikki dump → wiktionary.jsontests/                        # 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.

[PyPI]

Roadmap

  • Grow the curated set, especially idioms and proverbs (કહેવત)
  • Sense-level synonyms instead of a merged list
  • Better verb lemmatization
  • Streamable HTTP transport and a hosted endpoint
  • Publish to PyPI and the MCP Registry

License

  • Code: MIT
  • Wiktionary-derived data (src/gujarati_lexicon_mcp/data/wiktionary.json): CC BY-SA, see Wiktionary:Copyrights

Built by Aarsh Dhokai · AI × AI: Artificial Intelligence × Aarsh India

Source: README.md at commit a92d798

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.2.1LatestOct 8, 2026