VRAMGlass — Claude Code MCP server: what it does, how to install
Fetches live GPU prices, checks VRAM requirements for local LLMs, and helps build PC rigs inside your coding assistant.
claude mcp add --transport http mcp https://mcp.vramglass.com/mcpWhat VRAMGlass 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.
What it helps with
- 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 for the agent
- 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
How to install VRAMGlass
Platform CLI: remote server
claude mcp add --transport http mcp https://mcp.vramglass.com/mcpPlatform CLI: remote server
codex mcp add vramglass --url https://mcp.vramglass.com/mcpConfig file
{
"mcpServers": {
"vramglass": {
"url": "https://mcp.vramglass.com/mcp"
}
}
}Config file
{
"servers": {
"vramglass": {
"type": "http",
"url": "https://mcp.vramglass.com/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http vramglass https://mcp.vramglass.com/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about VRAMGlass
How to install VRAMGlass in Claude Code?
Run claude mcp add --transport http vramglass https://mcp.vramglass.com/mcp in your CLI. To authenticate requests, pass your API key header during setup.
What does VRAMGlass do?
It provides live GPU marketplace prices, rental rates, and hardware compatibility checks for running open-source LLMs locally.
Is a paid account required to access the server?
No, access is free, but you must register an account on vramglass.com to generate an API key or authenticate with OAuth. Excessive request volumes trigger standard rate limits.
