data-science-mcp 0.22.0

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

CLI or API | MCP | Agent

Version: 0.22.0

---

Overview

Data Science Mcp is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Data Science MCP Server — Model training, evaluation, and evolution tools for agentic ML workflows. Integrates with agent-utilities IModelEvolver (CONCEPT:AHE-3.8)..

---

Key Features

• Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
• Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.
• In-House Model Training (Wave C): A deterministic SFT/DPO/GRPO corpus + reward engine plus torch/PEFT gradient trainers (LoRA/QLoRA, TIES adapter merge, vLLM rollouts, checkpoint→reliability-suite eval hooks). Loss/optimizer kernels are CPU-smoke-tested on a toy model; real fine-tunes run on the GB10. Install with pip install data-science-mcp[training]. MCP tools: build_training_dataset, compose_reward, train_sft, train_dpo, train_grpo, merge_adapters_ties. See docs/training.md.

---

CLI or API

This agent wraps the Data Science MCP Server — Model training, evaluation, and evolution tools for agentic ML workflows. Integrates with agent-utilities IModelEvolver (CONCEPT:AHE-3.8). API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.

---

MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool Module	Toggle Env Var	Enabled by Default	Description & Nested Methods
Model Training	MODEL_TRAININGTOOL	True	Fit a machine learning model on a dataset and return metrics.
Model Evolution	MODEL_EVOLUTIONTOOL	True	Submit a model to the evolutionary Pareto frontier.
Interpretability	INTERPRETABILITYTOOL	True	Generate a structured suite of 6 interpretability test cases for a model.
Data Management	DATA_MANAGEMENTTOOL	True	Load and parse a dataset by name or CSV file path.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

---

MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "data-science-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "data-science-mcp",
        "data-science-mcp"
      ],
      "env": {
        "DATA_SCIENCE_MCP_URL": "your_data_science_mcp_url_here",
        "DATA_SCIENCE_MCP_TOKEN": "your_data_science_mcp_token_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "data-science-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "data-science-mcp",
        "data-science-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "DATA_SCIENCE_MCP_URL": "your_data_science_mcp_url_here",
        "DATA_SCIENCE_MCP_TOKEN": "your_data_science_mcp_token_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "data-science-mcp": {
      "url": "http://localhost:8000/data-science-mcp/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name data-science-mcp-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e DATA_SCIENCE_MCP_URL="your_value" \
  -e DATA_SCIENCE_MCP_TOKEN="your_value" \
  knucklessg1/data-science-mcp:latest

---

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export DATA_SCIENCE_MCP_URL="your_value"
export DATA_SCIENCE_MCP_TOKEN="your_value"

# Run the agent server
data-science-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  data-science-mcp-mcp:
    image: knucklessg1/data-science-mcp:latest
    container_name: data-science-mcp-mcp
    hostname: data-science-mcp-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  data-science-mcp-agent:
    image: knucklessg1/data-science-mcp:latest
    container_name: data-science-mcp-agent
    hostname: data-science-mcp-agent
    restart: always
    depends_on:
      - data-science-mcp-mcp
    env_file:
      - ../.env
    command: [ "data-science-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://data-science-mcp-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9004:9004"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9004/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.

---

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Feature	Functionality	Enablement
Tool Guard	Sensitivity inspection with human-in-the-loop validation	Enabled by default
Prompt Injection Defense	Input scanning, repetition monitoring, and recursive loop blocks	Enabled by default
Context Safety Guard	Stuck-loop detectors and contextual overflow preemptive alerts	Enabled by default

---

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install data-science-mcp[all]

# Using standard pip
python -m pip install data-science-mcp[all]

---

Repository Owners

---

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Execute test suites using pytest