# RigBase

The RigBase MCP server for Claude Code gives agents access to home PC builds and measured local language model speeds. Search configurations, compare results, or look for a GPU suited to a model.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: getrigbase
- License: CC-BY-4.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/getrigbase/rigbase-data
- Updated: 2026-11-06
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/rigbase

## What it does

RigBase lets an agent search data about home computer builds and reported speeds for local language models. It can help find configurations, compare benchmark results, and look up GPUs used with a model.

RigBase gathers figures from public sources rather than running its own tests. Results vary by source, engine, quantization, and settings, so speed comparisons are most useful within the same source. Connect to the MCP server at `https://getrigbase.com/mcp`.

## Requirements
- Remote server: `https://getrigbase.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http rigbase https://getrigbase.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add rigbase --url https://getrigbase.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "rigbase": {
            "url": "https://getrigbase.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "rigbase": {
            "type": "http",
            "url": "https://getrigbase.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http rigbase https://getrigbase.com/mcp
```

## When to use it
- find builds measured with a particular model
- compare generation speeds across configurations
- look up GPUs used for a local model
- check which hardware configurations ran a model

## Example prompts
- Find builds with `Llama` speed results and compare their generation rates.
- Which GPUs appear in builds with strong results for this model?
- Search for hardware configurations that ran this model.

## Similar
- [Guaardvark](https://affpapa.org/en/nevibecode/mcp/guaardvark.md) — MCP server · ★ 354 repo stars
- [mirofish-offline-simulation](https://affpapa.org/en/nevibecode/skills/mirofish-offline-simulation.md) — skill · 1400 installs
- [Local Model Suitability MCP](https://affpapa.org/en/nevibecode/mcp/local-model-suitability-mcp.md) — MCP server · 2764 installs
- [mac-code-local-ai-agent](https://affpapa.org/en/nevibecode/skills/mac-code-local-ai-agent.md) — skill · 851 installs
- [openclaw-local-mac-mini](https://affpapa.org/en/nevibecode/skills/openclaw-local-mac-mini.md) — skill · 346 installs
- [KIAgent](https://affpapa.org/en/nevibecode/mcp/kiagent.md) — MCP server · ★ 7 repo stars

---
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
