MCP NLP Analytics

Provides persistent sentiment analytics, churn risk scoring, alerts, and reporting via an MCP server that can be used with Claude Desktop.

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rubenreyesss-mcp-nlp-analytics": {
      "command": "python",
      "args": [
        "src/mcp_server.py"
      ]
    }
  }
}

Sentiment Evolution Tracker is an MCP server that adds persistent sentiment analytics, churn risk scoring, alerting, and reporting to Claude-enabled workflows. It lets you analyze conversations, detect risk, and generate portfolio-level insights with historical memory and real-time updates, either as a standalone service or alongside Claude Desktop.

How to use

You use this MCP server by running it locally and connecting your MCP client (such as Claude Desktop) to it. Start the server, then invoke any of the seven sentiment tools from your MCP client to analyze conversations, retrieve customer histories, or generate reports. The server maintains persistent data, computes trend trajectories, flags churn signals, and emits alerts when risk thresholds are exceeded. You can ask Claude to pull a customer’s timeline, forecast next actions, and save analyses with full metadata.

How to install

Prerequisites: you must have Python 3.10 or newer and a working Python environment.

# 1) Clone the project repository
git clone https://github.com/RubenReyesss/mcp-nlp-analytics.git
cd mcp-nlp-server

# 2) Install Python dependencies
pip install -r requirements.txt

# 3) Download necessary NLP corpora
python -m textblob.download_corpora
python -m nltk.downloader punkt averaged_perceptron_tagger

Practical setup steps include initializing the database, loading deterministic demo data, and starting auxiliary dashboards before launching the MCP server.

# 4) Initialize database and load demo data
python init_db.py
python tools/populate_demo_data.py

# 5) Start the terminal dashboard (optional)
python tools/dashboard.py

# 6) Generate an HTML report (optional)
python tools/generate_report.py

# 7) Run the MCP server (start command for Claude Desktop integration)
python src/mcp_server.py

Additional sections

Configuration and integration details are focused on connecting Claude Desktop to the local MCP server. The MCP server exposes a local command to launch the service, and the client can invoke tools to analyze sentiment evolution, detect risk signals, predict next actions, retrieve history, identify high-risk customers, gather statistics, and persist analyses.

Available tools

analyze_sentiment_evolution

Calculates sentiment trajectory for a set of messages.

detect_risk_signals

Flags phrases that correlate with churn or dissatisfaction.

predict_next_action

Forecasts CHURN / ESCALATION / RESOLUTION outcomes.

get_customer_history

Retrieves full timeline, sentiment, and alerts for a customer.

get_high_risk_customers

Returns customers whose churn risk is above a threshold.

get_database_statistics

Portfolio-level KPIs (customers, alerts, sentiment mean).

save_analysis

Persists a custom analysis entry with full metadata.