Osseni94/oyemi-mcp

MCP (Model Context Protocol) server for the Oyemi semantic lexicon. Provides deterministic word-to-code mapping and valence analysis for AI agents like Claude, ChatGPT, and Gemini.
Features
- **Semantic Encoding**: Convert words to deterministic semantic codes
- **Valence Analysis**: Analyze text sentiment using lexicon-based valence
- **Semantic Similarity**: Measure how similar two words are
- **Synonym/Antonym Lookup**: Find related words
- **Zero Runtime Dependencies**: No external NLP libraries needed at runtime
Installation
Or install from source:
Configuration
Claude Desktop
Add to your claude_desktop_config.json:
Claude Code
Add to your MCP settings:
Available Tools
encode_word
Encode a word to its semantic code.
analyze_text
Analyze the valence/sentiment of text.
semantic_similarity
Compare two words semantically.
find_synonyms
Find synonyms for a word.
find_antonyms
Find antonyms for a word.
batch_encode
Encode multiple words at once.
get_lexicon_info
Get information about the lexicon.
Code Format
Oyemi codes follow the format HHHH-LLLLL-P-A-V:
| Component | Description | Values |
|-----------|-------------|--------|
| HHHH | Semantic superclass | 4-digit category code |
| LLLLL | Synset ID | 5-digit unique identifier |
| P | Part of speech | 1=noun, 2=verb, 3=adj, 4=adv |
| A | Abstractness | 0=concrete, 1=mixed, 2=abstract |
| V | Valence | 0=neutral, 1=positive, 2=negative |
Use Cases
- **AI Sentiment Analysis**: Let AI agents understand emotional tone
- **Semantic Grounding**: Provide concrete valence scores instead of guessing
- **Text Analysis**: Analyze documents, reviews, feedback
- **Word Relationships**: Find synonyms, antonyms, similar words
License
MIT License
Author
Kaossara Osseni - grandnasser.com