# VRAMGlass

Fetches live GPU prices, checks VRAM requirements for local LLMs, and helps build PC rigs inside your coding assistant.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: vramglass
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/vramglass/mcp
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/vramglass

## What it does

VRAMGlass connects as a remote Streamable HTTP server to supply your assistant with hardware stats directly from vramglass.com. It answers questions about memory requirements for specific model quantizations, context windows, and compatible graphics cards.

Under the hood, read-only tools like `get_prices`, `models_for_gpu`, and `recommend_build` handle queries without modifying any data. The server pulls asking prices across eBay, Xianyu, and Amazon Japan every 6 hours, calculating median figures. It also retrieves rental rates from RunPod, Vast.ai, and Compshare.

No local code installation is involved. To query the server, you need a free VRAMGlass account and an API token passed via `Authorization: Bearer YOUR_KEY` or through OAuth. Keep in mind that reported VRAM usage and speeds represent planning estimates rather than measured benchmarks.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- calculate required VRAM for a model quantization and context length
- check current marketplace prices for used GPUs like RTX 3090
- plan complete PC hardware configurations under a specific budget
- compare hourly GPU rental costs across cloud providers

## Example prompts
- How much VRAM does Qwen 27B require at 4-bit with 32K context?
- What is the current median asking price for an RTX 4090 on eBay?
- Recommend a PC build for running DeepSeek with a 5000 dollar limit

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16741
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 108044
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26711
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23288
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9370
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9301

---
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