MCP Chat Analysis Server

Provides semantic analysis, semantic search, and knowledge-graph capabilities for chat conversations via MCP.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 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": {
    "rebots-online-mcp-chat-analysis-server": {
      "command": "python",
      "args": [
        "-m",
        "mcp_chat_analysis.server"
      ],
      "env": {
        "NEO4J_URL": "bolt://localhost:7687",
        "NEO4J_USER": "neo4j",
        "QDRANT_URL": "http://localhost:6333",
        "NEO4J_PASSWORD": "your-password"
      }
    }
  }
}

You can use the MCP Chat Analysis Server to perform semantic analysis of chat conversations, search by meaning, explore knowledge relationships, and extract insights from conversations. It integrates with MCP-compatible clients to provide scalable analysis and discovery across chat data.

How to use

Set up the MCP server locally and connect it to your MCP client. Start the server, then configure your MCP client to point to this server. Use the provided commands to run the server and the available tools to import conversations, perform semantic search, analyze metrics, and extract concepts. The server exposes semantic capabilities via an MCP-compatible interface, so your client can trigger actions such as importing data, querying by semantic similarity, and inspecting knowledge graphs.

How to install

Prerequisites: you need Python 3.8 or newer and a running environment for the required databases. Install the package, set up databases, and run the server as shown.

pip install mcp-chat-analysis-server

# Set up configuration
cp config.example.yml config.yml
# Edit config.yml with your database settings

# Run the server
python -m mcp_chat_analysis.server

Configuration and runtime environment

The server relies on environment variables to connect to its backing stores. You can provide these when starting the server or configure them in your environment file. The following variables are shown for integration and should be present in your environment when running with the MCP client.

QDRANT_URL=http://localhost:6333
NEO4J_URL=bolt://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your-password

Available tools

import_conversations

Import and analyze chat conversations from various export formats to populate the knowledge graph and embedding stores.

semantic_search

Query conversations by semantic similarity to retrieve relevant messages or threads.

analyze_metrics

Compute and report conversation metrics such as message frequency, response times, and topic diversity.

extract_concepts

Extract and analyze key concepts from conversations based on relevance and coverage.

Built by

VeilStrat

AI signals for GTM teams