Sentor MCP Server

Entity-based sentiment analysis for Claude, Cursor, Windsurf, and any MCP-compatible AI assistant.

Sentor is an entity-based sentiment analysis platform powered by fine-tuned BERT models. This MCP server exposes Sentor's ML APIs as tools your AI assistant can call directly — score sentiment toward specific entities in text, cluster documents by topic, and generate topic labels, all from a single natural-language prompt.

Table of Contents

• What It Does

• Requirements

• Quick Start

  • Claude Desktop

  • Cursor / Windsurf

  • Claude.ai Web (Remote MCP)

• Tools Reference

• Usage Examples

• Rate Limits

• Remote Deployment

• Links

Related MCP server: KeyNeg MCP Server

🎯 What It Does

Once connected, your AI assistant gains four tools:

Example prompt after setup:

"Analyse these 50 customer reviews for sentiment toward our checkout flow and delivery speed. Then cluster them by topic and name each cluster."

📋 Requirements

• Python 3.10+

• A Sentor API key — get one free at dashboard.sentor.app

🚀 Quick Start

Claude Desktop

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sentor": {
      "command": "uvx",
      "args": ["sentor-mcp"],
      "env": {
        "SENTOR_API_KEY": "your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop. A hammer icon appears in the tool selector — Sentor is ready.

No uvx? Install it with pip install uv, or use sentor-mcp directly after pip install sentor-mcp.

Cursor / Windsurf

Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "sentor": {
      "command": "uvx",
      "args": ["sentor-mcp"],
      "env": {
        "SENTOR_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude.ai Web (Remote MCP)

Run the HTTP server and connect by URL:

docker run -e SENTOR_API_KEY=your_api_key -p 8080:8080 ghcr.io/nikx-tech/sentor-mcp:latest

Then in Claude.ai → Settings → Integrations → Add MCP Server:

http://your-server:8080/sse

🔧 Tools Reference

analyze_sentiment(docs, language="en")

Analyse entity-level sentiment in one or more documents.

docs = [
    {
        "doc_id": "review-1",
        "doc": "The delivery was fast but the packaging was completely crushed.",
        "entities": ["delivery", "packaging"]
    }
]
# Returns: predicted_label, probabilities, per-sentence details

Supported languages: en (English), nl (Dutch)

cluster_documents(documents, language="en")

Group documents into thematic clusters. Requires at least 5 documents.

documents = [
    {"doc_id": "r1", "text": "Great product quality, very happy.", "entities": ["product"]},
    # ... at least 5 documents
]
# Returns: clusters with cluster_id, document_count, documents, top_words
# Cluster -1 = outliers that did not fit any topic

name_topic(cluster_id, documents, top_words, entities, language="en")

Generate a short label for a cluster. Pass data directly from cluster_documents output.

name_topic(
    cluster_id=0,
    documents=cluster["documents"],
    top_words=cluster["top_words"],
    entities=["BrandName"],  # exclude your brand from the label
    language="en"
)
# Returns: { "topic_name": "Shipping Delay Complaints", "generation_method": "LLM" }

health_check()

# Returns: { "status": "healthy", "version": "1.0.0", "llm_status": "available" }

💬 Usage Examples

Single document:

"Use Sentor to analyse the sentiment of this review toward Apple and iPhone: [paste text]"

Batch analysis:

"I have 100 customer reviews. Use Sentor to score sentiment toward 'delivery' and 'support' in each one, then tell me the ratio of positive to negative."

Full pipeline:

"Use Sentor to: 1) analyse sentiment in these 200 reviews for 'product quality' and 'price', 2) cluster them by topic, 3) name each cluster, 4) summarise the findings."

Competitive analysis:

"Analyse these tweets for sentiment toward Apple, Samsung, and Google separately using Sentor, then compare the results."

📊 Rate Limits

View full pricing →

🐳 Remote Deployment

Run as a hosted HTTP/SSE server for AI tools that support remote MCP endpoints.

Docker:

docker build -t sentor-mcp .
docker run \
  -e SENTOR_API_KEY=your_key \
  -p 8080:8080 \
  sentor-mcp

The server exposes:

• GET /sse — SSE stream (MCP transport)

• POST /messages — message endpoint

Environment variables:

🔗 Links

• Sentor Dashboard — manage API keys, projects, and usage

• API Documentation — full REST API reference

• MCP Integration Guide — step-by-step setup

• PyPI Package — pip install sentor-mcp

• Support