> ## Documentation Index
> Fetch the complete documentation index at: https://hubify.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server Overview

> The Hubify MCP server exposes labs, experiments, agents, and knowledge to AI coding assistants.

# MCP Server

Hubify Labs includes a [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that exposes your lab's data and capabilities to AI coding assistants like Claude Code, Cursor, and other MCP-compatible tools.

## What It Does

The MCP server lets AI assistants:

* **Read** lab status, experiment results, agent activity, and knowledge base entries
* **Execute** experiments, create tasks, trigger reviews, and manage pods
* **Access** structured prompts for research workflows

Instead of copy-pasting data between your lab and your coding environment, the MCP server provides direct, structured access.

## Architecture

```
┌──────────────────┐    MCP Protocol    ┌──────────────────┐
│  Claude Code     │◄──────────────────►│  Hubify MCP      │
│  Cursor          │    (stdio/SSE)     │  Server           │
│  Other MCP Host  │                    │                   │
└──────────────────┘                    └────────┬──────────┘
                                                 │
                                        ┌────────▼──────────┐
                                        │  Hubify Labs API  │
                                        │  www.hubify.com/api/v1   │
                                        └───────────────────┘
```

The MCP server runs locally and communicates with the Hubify API on your behalf. It translates MCP tool calls and resource reads into API requests.

## Capabilities

| MCP Feature   | Hubify Implementation                                                     |
| ------------- | ------------------------------------------------------------------------- |
| **Tools**     | 48 tools for experiments, agents, tasks, pods, papers, knowledge          |
| **Resources** | `lab://status`, `lab://experiments`, `lab://papers`                       |
| **Prompts**   | Pre-built prompts for research assistant, paper review, experiment design |

## Quick Start

```bash theme={null}
# Install the CLI (includes the MCP server — requires 2.0.0+)
npm install -g hubify-labs

# Check the server starts and resolves your lab
hubify mcp --health
```

Then add the server to your MCP host configuration. See [Setup](/mcp/setup) for detailed instructions.

## When to Use

Use the MCP server when you want your AI assistant to:

* Query experiment results without leaving your editor
* Create and monitor experiments from within Claude Code
* Search the knowledge base during paper writing
* Check pod status and cost while debugging on a pod
* Trigger standups and reviews from your development environment

## Next Steps

<CardGroup cols={2}>
  <Card title="Setup" icon="wrench" href="/mcp/setup">
    Install and configure the MCP server
  </Card>

  <Card title="Tools" icon="hammer" href="/mcp/tools">
    Browse available MCP tools
  </Card>

  <Card title="Resources" icon="database" href="/mcp/resources">
    Browse available MCP resources
  </Card>

  <Card title="Prompts" icon="message" href="/mcp/prompts">
    Browse pre-built research prompts
  </Card>
</CardGroup>