Metadata-Version: 2.5
Name: custovox-review-analyzer
Version: 1.0.0
Summary: Customer review analysis MCP: sentiment breakdown, summaries of positive and negative reviews. Multilingual sentiment. By custovox.ai
Project-URL: Homepage, https://custovox.ai
Project-URL: Repository, https://github.com/jeremdecustovox/custovox-ai
Project-URL: Documentation, https://custovox.ai
Author-email: Jérémie Muselet <jeremie@custovox.ai>
License: MIT
Keywords: customer-experience,custovox,mcp,nlp,review-analysis,sentiment
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: mcp<2,>=1.0.0
Requires-Dist: torch>=2.0.0
Requires-Dist: transformers>=4.40.0
Description-Content-Type: text/markdown

# custovox-review-analyzer

<!-- mcp-name: io.github.jeremdecustovox/custovox-review-analyzer -->

Customer review analysis MCP server.

## What it returns
- Overall sentiment and average score (Very Negative → Very Positive)
- Sentiment breakdown (count and % per level)
- Up to 3 sentences summarizing the positive reviews, and 3 for the negative ones
- A simple recommendation based on the share of negative reviews

Sentiment is multilingual (EN/FR/DE/ES/PT-BR). The summaries use an English model
(facebook/bart-large-cnn): they are most accurate on English reviews.
Up to 100 reviews per call; the summaries are based on the first 10 positive and 10 negative reviews.

## Installation
pip install custovox-review-analyzer

The models (about 2 GB) are downloaded from Hugging Face on first start and run on your machine.

## Need more?
**custovox.ai** — Full customer intelligence platform. From $89/month.
https://custovox.ai
