# EasyDeploy AI

The EasyDeploy AI MCP server for Claude Code connects EasyDeploy tools to machine-learning tasks. It supports model training from CSV files and prediction runs.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: EasyDeploy-AI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/EasyDeploy-AI/easydeploy-ai-mcp
- Updated: 2026-11-05
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/easydeploy-ai

## What it does

The server exposes EasyDeploy API tools to an MCP client. An agent can find models, engineer features, tune settings, train models, and request predictions. The `get_started` tool returns a workflow guide bundled with the package; reading it does not call the API.

The agent handles data preparation, target selection, splitting, and evaluation on a test set. EasyDeploy does not clean the data or choose the target variable. Connection uses the hosted endpoint `https://mcp.easydeploy.ai/mcp`, and access requires signing in to an EasyDeploy account.

## Requirements
- Remote server: `https://mcp.easydeploy.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http easydeploy-ai-mcp https://mcp.easydeploy.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add easydeploy-ai --url https://mcp.easydeploy.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "easydeploy-ai": {
            "url": "https://mcp.easydeploy.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "easydeploy-ai": {
            "type": "http",
            "url": "https://mcp.easydeploy.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http easydeploy-ai https://mcp.easydeploy.ai/mcp
```

## When to use it
- train a model from a CSV file
- generate predictions for a test dataset
- evaluate a model on held-out data
- tune model features and settings

## Example prompts
- Train an EasyDeploy model from my CSV files and evaluate it on the test data.
- Prepare these data for EasyDeploy training, then run predictions.
- Show the EasyDeploy guide for the model-training workflow.

## Similar
- [sap-hana-ml](https://affpapa.org/en/nevibecode/skills/sap-hana-ml.md) — skill · 821 installs
- [automl-hyperparameter-optimization](https://affpapa.org/en/nevibecode/skills/automl-hyperparameter-optimization.md) — skill · 110 installs
- [Stats Compass](https://affpapa.org/en/nevibecode/mcp/stats-compass.md) — MCP server · ★ 16 repo stars
- [AutoTS](https://affpapa.org/en/nevibecode/mcp/autots.md) — MCP server · ★ 1432 repo stars
- [SAS Viya](https://affpapa.org/en/nevibecode/mcp/sas-viya.md) — MCP server · ★ 70 repo stars
- [tao-run-automl-deft-pipeline](https://affpapa.org/en/nevibecode/skills/tao-run-automl-deft-pipeline.md) — skill · 1600 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
