review-analyzer-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REVIEW_ANALYZER_DATA | No | Review corpus (.csv or .json); 'demo' selects the 5-review synthetic file | data/processed/amazon_electronics/analytics_corpus.csv |
| REVIEW_ANALYZER_ASPECTS | No | Aspect lexicon | configs/aspects.json |
| REVIEW_ANALYZER_MODEL_DIR | No | Serve a specific model artifact | from artifacts/models/selected.json |
| REVIEW_ANALYZER_RETRIEVER | No | 'lsa', or 'sentence-transformers' (needs .[semantic]) | lsa |
| REVIEW_ANALYZER_MAX_TEXT_CHARS | No | Maximum analyze_sentiment input length | 5000 |
| REVIEW_ANALYZER_EMBEDDING_MODEL | No | Model for the dense retriever | sentence-transformers/all-MiniLM-L6-v2 |
| REVIEW_ANALYZER_SENTIMENT_BACKEND | No | 'trained', or 'keyword' for the explicit demo baseline | trained |
| REVIEW_ANALYZER_MIN_PRODUCT_REVIEWS | No | Reviews below which a product summary is flagged as a small sample (a heuristic) | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues