Prometheux MCP Server

A Model Context Protocol (MCP) client that enables AI agents like Claude to interact with Prometheux knowledge graphs and reasoning capabilities.

For Users

What This Does

This package lets you use Claude Desktop to interact with your Prometheux projects:

• List concepts in your projects

• Run concepts to derive new knowledge

• All through natural conversation with Claude

Prerequisites

• Prometheux account with access to a deployed instance

• Claude Desktop installed on your machine

• Your authentication token from your Prometheux account settings

Installation

Option 1: Automated Install (Recommended)

The easiest way to install - download and run our installation script:

macOS/Linux:

curl -sSL https://raw.githubusercontent.com/prometheuxresearch/px-mcp-server/main/install.sh -o install.sh
chmod +x install.sh
./install.sh

Windows (PowerShell):

Invoke-WebRequest -Uri "https://raw.githubusercontent.com/prometheuxresearch/px-mcp-server/main/install.ps1" -OutFile "install.ps1"
.\install.ps1

The script will:

• ✅ Install pipx (if not already installed)

• ✅ Install prometheux-mcp package

• ✅ Prompt for your credentials (URL, token, username, organization)

• ✅ Automatically configure Claude Desktop

• ✅ Create backups of existing configuration

Then just restart Claude Desktop and you're ready!

Option 2: Manual Install Using pipx

If you prefer manual installation, use pipx to install the package in an isolated environment:

macOS:

brew install pipx
pipx ensurepath
pipx install prometheux-mcp

Windows:

pip install pipx
pipx ensurepath
pipx install prometheux-mcp

Linux:

pip install pipx
pipx ensurepath
pipx install prometheux-mcp

Configuration

Note: If you used the automated installation script (Option 1), configuration was done automatically. Skip to the "Using Prometheux with Claude" section below.

For manual installations (Option 2):

1. Get your credentials from your Prometheux account settings:

   • Server URL (e.g., https://api.prometheux.ai)

   • Authentication token

   • Username

   • Organization

2. Configure Claude Desktop by editing the config file:

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

   Configuration Example:

   {
     "mcpServers": {
       "prometheux": {
         "command": "/Users/YOUR_USERNAME/.local/bin/prometheux-mcp",
         "args": ["--url", "https://api.prometheux.ai"],
         "env": {
           "PROMETHEUX_TOKEN": "your_token_here",
           "PROMETHEUX_USERNAME": "your_username",
           "PROMETHEUX_ORGANIZATION": "your_org"
         }
       }
     }
   }

   Finding Your Path: Run this in your terminal to find the full path:

   • macOS/Linux: which prometheux-mcp

   • Windows: where prometheux-mcp (in PowerShell or Command Prompt)

   Common paths after pipx install:

   • macOS: /Users/YOUR_USERNAME/.local/bin/prometheux-mcp

   • Windows: C:\\Users\\YOUR_USERNAME\\.local\\bin\\prometheux-mcp.exe (use double backslashes in JSON)

   • Linux: /home/YOUR_USERNAME/.local/bin/prometheux-mcp

   Note: Username and organization are required for API routing through the gateway.

   Custom URLs: For on-premise deployments or custom URLs, replace https://api.prometheux.ai with your own server URL.

3. Restart Claude Desktop (quit completely with Cmd+Q, then reopen)

Usage

Once configured, just chat with Claude:

"What concepts are available in project customer-analytics?"

"Run the churn_prediction concept in project customer-analytics"

"Show me the high_value_customers from project sales-data with min_value of 1000"

Available Tools

Troubleshooting

"command not found" or "Server disconnected" errors:

macOS:

1. Find the full path: which prometheux-mcp

2. Use that full path in your config (usually /Users/YOUR_USERNAME/.local/bin/prometheux-mcp)

3. If still having issues, try pipx: pipx install prometheux-mcp

4. Restart Claude Desktop completely (Cmd+Q, then reopen)

Windows:

1. Find the full path: where prometheux-mcp (in PowerShell or Command Prompt)

2. Use that full path in your config with double backslashes (e.g., C:\\Users\\YOUR_USERNAME\\.local\\bin\\prometheux-mcp.exe)

3. Restart Claude Desktop

"Connection refused" error: Check that your Prometheux server URL is correct and accessible. Test with: curl [YOUR_URL]/mcp/info

"Authentication failed" error: Verify your token is correct in the config. Generate a new token from your Prometheux account settings if needed.

Check logs:

• macOS: ~/Library/Logs/Claude/mcp-server-prometheux.log

• Windows: %APPDATA%\Claude\logs\mcp-server-prometheux.log

Related MCP server: A2A MCP Server

Tool Reference

list_concepts

Lists all concepts available in a project.

Parameters:

Example response:

{
  "concepts": [
    {
      "predicate_name": "customer",
      "fields": {"id": "string", "name": "string"},
      "column_count": 2,
      "is_input": true,
      "row_count": 1000,
      "type": "postgresql",
      "description": "Customer records"
    }
  ],
  "count": 1
}

run_concept

Executes a concept to derive new knowledge through Vadalog reasoning.

Parameters:

Example response:

{
  "concept_name": "high_value_customers",
  "message": "Concept executed successfully",
  "evaluation_results": {
    "resultSet": {
      "high_value_customers": [["Alice", 5000], ["Bob", 3000]]
    },
    "columnNames": {
      "high_value_customers": ["name", "total_value"]
    }
  },
  "predicates_populated": ["high_value_customers"],
  "total_records": 2
}

For Maintainers

Releasing a New Version

# 1. Update version
echo "0.1.6" > version.txt

# 2. Build and publish to PyPI
python -m build
twine upload dist/*

# 3. Commit and tag
git add version.txt
git commit -m "Release version 0.1.6"
git push
git tag v0.1.6
git push origin v0.1.6

Users will automatically get the new version when they run the installation script or pipx install prometheux-mcp.

Access to Prometheux Backend

The Prometheux backend is required to use this MCP client. To request access:

• 📧 Email: davben@prometheux.co.uk, teodoro.baldazzi@prometheux.co.uk, or support@prometheux.co.uk

• 🌐 Website: https://www.prometheux.ai

License

BSD 3-Clause License — see LICENSE file for details.

About Prometheux

Prometheux is an ontology native data engine that processes data anywhere it lives. Define ontologies once and unlock knowledge that spans databases, warehouses, and platforms—built on the Vadalog reasoning engine.

Key capabilities:

• Connect: Query across Snowflake, Databricks, Neo4j, SQL, CSV, and more without ETL or vendor lock-in

• Think: Replace 100+ lines of PySpark/SQL with simple declarative logic. Power graph analytics without GraphDBs

• Explain: Full lineage & traceability with deterministic, repeatable results. Ground AI in structured, explainable context

Exponentially faster and simpler than traditional approaches. Learn more at prometheux.ai.

Support

For issues, questions, or access requests:

• Homepage: https://www.prometheux.ai

• PyPI: https://pypi.org/project/prometheux-mcp/

• Email: davben@prometheux.co.uk, teodoro.baldazzi@prometheux.co.uk, or support@prometheux.co.uk

• Documentation: https://docs.prometheux.ai/mcp

• Issues: GitHub Issues

Related Projects

• Prometheux Chain — Python SDK for Prometheux

• Vadalog Extension — JupyterLab extension for Vadalog

• Vadalog Jupyter Kernel — Jupyter kernel for Vadalog