Chat Analysis MCP Server

Enables semantic analysis of chat conversations through vector embeddings and knowledge graphs.

Local serverstdioPython 12

What is the Chat Analysis MCP server?

Chat Analysis MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Enables semantic analysis of chat conversations through vector embeddings and knowledge graphs.

What you get

A Model Context Protocol (MCP) server that enables semantic analysis of chat conversations through vector embeddings and knowledge graphs. This server provides tools for analyzing chat data, performing semantic search, extracting concepts, and analyzing conversation patterns.

  • 🔍 Semantic Search: Find relevant messages and conversations using vector similarity
  • 🕸️ Knowledge Graph: Navigate relationships between messages, concepts, and topics
  • 📊 Conversation Analytics: Analyze patterns, metrics, and conversation dynamics
  • 🔄 Flexible Import: Support for various chat export formats
  • 🚀 MCP Integration: Easy integration with Claude and other MCP-compatible systems

What the assistant can call

Once Chat Analysis is connected, these are the calls the assistant has available:

  • import_conversations — Import and analyze chat conversations python { "source_path": "/path/to/export.zip", "format": "openai_native" # or html, markdown, json }
  • semantic_search — Search conversations by semantic similarity python { "query": "machine learning applications", "limit": 10, "min_score": 0.7 }
  • analyze_metrics — Analyze conversation metrics python { "conversation_id": "conv-123", "metrics": [ "message_frequency", "response_times", "topic_diversity" ] }
  • extract_concepts — Extract and analyze concepts python { "conversation_id": "conv-123", "min_relevance": 0.5, "max_concepts": 10 }

Configuration and credentials

You will need 4 environment variables: QDRANT_URL, NEO4J_URL, NEO4J_USER, NEO4J_PASSWORD. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.8+ - Neo4j database for knowledge graph storage - Qdrant vector database for semantic search - sentence-transformers for embeddings

Setting it up

The server ships on PyPI as mcp-chat-analysis-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Chat Analysis's toolset — import_conversations, semantic_search, analyze_metrics and 1 more — is a fair guide to whether it matches your workflow. It is maintained by rebots-online; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the chat analysis mcp server does with a few real requests.

Available tools

ToolWhat it does
import_conversationsImport and analyze chat conversations python { "source_path": "/path/to/export.zip", "format": "openai_native" # or html, markdown, json }
semantic_searchSearch conversations by semantic similarity python { "query": "machine learning applications", "limit": 10, "min_score": 0.7 }
analyze_metricsAnalyze conversation metrics python { "conversation_id": "conv-123", "metrics": [ "message_frequency", "response_times", "topic_diversity" ] }
extract_conceptsExtract and analyze concepts python { "conversation_id": "conv-123", "min_relevance": 0.5, "max_concepts": 10 }

How to install the Chat Analysis MCP server

{
  "mcpServers": {
    "chat-analysis": {
      "command": "uvx",
      "args": ["mcp-chat-analysis-server"],
      "env": {
        "QDRANT_URL": "your-value",
        "NEO4J_URL": "your-value",
        "NEO4J_USER": "your-value",
        "NEO4J_PASSWORD": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.8+ - Neo4j database for knowledge graph storage - Qdrant vector database for semantic search - sentence-transformers for embeddings
VariableDescriptionRequired
QDRANT_URLEndpoint or connection string the server talks to.Yes
NEO4J_URLEndpoint or connection string the server talks to.Yes
NEO4J_USERConfiguration value read at startup.Optional
NEO4J_PASSWORDConfiguration value read at startup.Optional

Example prompts to try

  • Use Chat Analysis to import conversations.
  • Use Chat Analysis to semantic search.
  • Use Chat Analysis to analyze metrics.

Frequently asked questions

Chat Analysis supports various chat export formats including OpenAI Native, HTML, Markdown, and JSON. This allows you to analyze data from diverse chat platforms and applications.