data-science-mcp 0.5.1

Data Science MCP Server — Model training, evaluation, and evolution tools for agentic ML workflows. Integrates with agent-utilities IModelEvolver (CONCEPT:AHE-3.15).

Data Science MCP - A2A | AG-UI | MCP

Version: 0.5.1

Overview

Data Science MCP MCP Server + A2A Agent

Data Science MCP Server — Model training, evaluation, and evolution tools for agentic ML workflows. Integrates with agent-utilities IModelEvolver (CONCEPT:AHE-3.15).

This repository is actively maintained - Contributions are welcome!

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

• DATA_SCIENCE_MCP_URL: The URL of the target service.
• DATA_SCIENCE_MCP_TOKEN: The API token or access token.

Run in stdio mode (default):

export DATA_SCIENCE_MCP_URL="http://localhost:8080"
export DATA_SCIENCE_MCP_TOKEN="your_token"
data-science-mcp --transport "stdio"

Run in HTTP mode:

export DATA_SCIENCE_MCP_URL="http://localhost:8080"
export DATA_SCIENCE_MCP_TOKEN="your_token"
data-science-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export DATA_SCIENCE_MCP_URL="http://localhost:8080"
export DATA_SCIENCE_MCP_TOKEN="your_token"
data-science-agent --provider openai --model-id gpt-4o --api-key sk-...

Security & Governance

This project is built on agent-utilities, inheriting enterprise-grade security and governance features.

Authentication & Authorization

Feature	Description
OIDC Token Delegation	RFC 8693 token exchange for user-context propagation from A2A → MCP
Eunomia Policies	Fine-grained, policy-driven tool authorization (none, embedded, remote)
Scoped Credentials	Tools execute with the caller's scoped identity where possible
3LO / OAuth / API Token	Multiple auth strategies with graceful fallback

Eunomia Policy Enforcement

Eunomia provides a policy enforcement point for all tool calls:

• Embedded mode: Load local mcp_policies.json for role-based access, sensitivity gating, and audit logging
• Remote mode: Forward authorization decisions to a central Eunomia policy server for multi-agent governance
• Enable via CLI: --eunomia-type embedded --eunomia-policy-file mcp_policies.json

Runtime Protections

Protection	Description
Tool Guard	Sensitivity detection with human-in-the-loop approval gating
Prompt Injection Defense	Input scanning and repetition/loop guards
Content Filtering	Output schema enforcement and cost budget controls
Stuck Loop Detection	Automatic detection and recovery from agent loops
Context Limit Warnings	Proactive alerts before context window exhaustion

Graph Agent Architecture

The A2A agent uses pydantic-graph orchestration with:

• RouterNode: Lightweight classifier that routes queries to specialized domains
• DomainNode: Focused executor with only relevant tools loaded, preventing tool hallucination
• Approval Gates: Policy-driven approval workflows before sensitive operations
• Usage Guards: Budget and rate limiting enforcement

Production Recommendation: Enable --eunomia-type embedded (or remote) + OIDC delegation + containerized deployment. See agent-utilities documentation for full policy configuration.

Docker

Build

docker build -t data-science-mcp .

Run MCP Server

docker run -d \
  --name data-science-mcp \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e DATA_SCIENCE_MCP_URL="http://your-service:8080" \
  -e DATA_SCIENCE_MCP_TOKEN="your_token" \
  knucklessg1/data-science-mcp:latest

Deploy with Docker Compose

services:
  data-science-mcp:
    image: knucklessg1/data-science-mcp:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - DATA_SCIENCE_MCP_URL=http://your-service:8080
      - DATA_SCIENCE_MCP_TOKEN=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "data-science": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "data-science-mcp",
        "data-science-mcp"
      ],
      "env": {
        "DATA_SCIENCE_MCP_URL": "http://your-service:8080",
        "DATA_SCIENCE_MCP_TOKEN": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install data-science-mcp

uv pip install data-science-mcp

Repository Owners