VRAMGlass

com.vramglassPublished by vramglass.comOfficial publisherv1.0.0Updated Oct 30, 2026

Live GPU prices, VRAM requirements and local LLM hardware planning from VRAMGlass.

VerifiedStreamable HTTPWeb executableFinanceAI & ML

Overview

AI-generated overview

Remote, read-only MCP server for live GPU and memory prices, VRAM requirements and local LLM hardware planning from VRAMGlass.

What you can do
  • Look up current GPU and memory prices on eBay, Xianyu and Amazon Japan, with median, range and listing count
  • Read daily price history up to a year and the GPU price index with its tiers
  • Search GPUs, memory and LLM models by name
  • Check which models a GPU can run and how much VRAM a model needs, with rough speed
  • Get PC build recommendations for a model, optionally within a budget, plus eBay deals and hourly rental prices on RunPod, Vast.ai and Compshare
When to use it
Useful when planning a local LLM setup or buying used hardware: comparing GPU asking prices across marketplaces, sizing VRAM for a model and context length, or budgeting a build. Also handy for tracking whether GPU prices are rising or falling.
Requirements
Remote Streamable HTTP endpoint; nothing to install. A free VRAMGlass account is required, either an API key sent in the Authorization header or OAuth sign-in for clients such as Claude and ChatGPT connectors. Network access to the hosted server.
Before you install
The Authorization header carries a secret API key that is shown only once; keep it private and revoke unused keys. Access tokens expire after 30 days without use or 180 days after authorization. Prices are median asking prices of current listings, not sold prices, and VRAM and speed figures are planning estimates. Buy and rental links carry referral parameters.

Installation

In SourceWeft

  1. Open VRAMGlass in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.vramglass%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "vramglass": {
      "type": "http",
      "url": "https://mcp.vramglass.com/mcp"
    }
  }
}

README

VRAMGlass MCP Server

Live GPU prices, VRAM requirements and local LLM hardware planning for your AI assistant, from VRAMGlass.

Connect it to Grok Bot, Claude, ChatGPT, Claude Code, Codex, Cursor or any MCP client, then ask in plain language. Answers come from the same data as vramglass.com, with links back to the source.

https://mcp.vramglass.com/mcp

Remote server, Streamable HTTP, read-only. Free; a VRAMGlass account is required.

Developer docs · 简体中文文档 · 日本語ドキュメント · MCP page · Methodology

What you can ask

  • "What does an RTX 3090 cost on eBay right now?"
  • "How much VRAM does Qwen3.8 27B need at 4-bit with a 32K context?"
  • "Which models can a DGX Spark run, and how fast?"
  • "Build me a PC for DeepSeek V4 Flash under $5,000."
  • "Are used GPU prices going up or down this month?"
  • "How much is renting an A100 per hour?"

For example, asked for RTX 3090 prices on October 22, 2026, the server returned a median eBay (US) asking price of $1,799 across 110 listings, ¥8,600 on Xianyu and ¥416,420 on Amazon.co.jp, each with its publish time and a link to the VRAMGlass page.

Connect

With an API key (recommended)

  1. Sign up or log in at vramglass.com/login. It's free; an email address is enough.

  2. Create a key under Your account → MCP connections. Give it a name, choose how long it stays valid and copy it right away; it is shown only once.

  3. Send this to your AI, with YOUR_KEY replaced by your key. Grok Bot, Claude Code, Codex, Manus, WorkBuddy and other assistants that can change their own settings add the server themselves:

    Please add a remote MCP server:Name: VRAMGlassURL: https://mcp.vramglass.com/mcpHeader: Authorization: Bearer YOUR_KEYOnce it's added, try it by checking what an RTX 4090 costs right now.

Manual configuration

Any client needs two things: the server URL and the header Authorization: Bearer YOUR_KEY. Choose HTTP (Streamable HTTP) as the transport.

Claude Code:

sh
claude mcp add --transport http vramglass https://mcp.vramglass.com/mcp --header "Authorization: Bearer YOUR_KEY"

Cursor and other clients that use mcp.json:

json
{  "mcpServers": {    "vramglass": {      "url": "https://mcp.vramglass.com/mcp",      "headers": { "Authorization": "Bearer YOUR_KEY" }    }  }}

With OAuth (no key)

Connectors in Claude (web and desktop) and ChatGPT can't take a key, so they sign in instead. Any other client that supports MCP OAuth works the same way.

  • Claude: Settings → Connectors → Add custom connector, and paste the server URL.
  • ChatGPT: Settings → Apps, turn on developer mode, then create an app with the server URL.

Your client opens the VRAMGlass login page. Log in with an email code or Google (an account is created if you don't have one), check the app name and return address on the consent page, and click Allow. The client renews access by itself; after 30 days without use, or 180 days after you authorized it, you sign in again.

Tools

The assistant picks the right tool by itself; you don't need to remember these names.

ToolWhat it returns
get_pricesCurrent prices for GPUs or memory on eBay, Xianyu and Amazon Japan: median, price range and listing count
get_price_historyDaily price history, from the last 7 days up to a year
get_price_indexThe GPU price index and its price tiers
search_hardwareFind GPUs and memory by name
search_modelsFind LLMs and their versions by name
models_for_gpuWhich models a GPU can run, and how long a context fits
gpus_for_modelHow much VRAM a model needs, which cards can run it and roughly how fast
recommend_buildPC builds for a model (GPU, CPU, motherboard, RAM, PSU) with an optional budget, prices and buy links; GPU options instead when the model fits entirely in VRAM
get_ebay_dealsThe eBay deals shown on GPU and memory pages: the same rule-filtered listings, up to six
get_rent_pricesHourly rental prices on RunPod, Vast.ai and Compshare

All tools are read-only. Results include a page_url and a cite line for attribution.

Keys, access and usage

  • A key or an authorized app can only read public price and spec data. It can't see your email, price alerts or watchlist, and it can't change anything in your account.
  • Use one key per tool so you can turn each one off separately. Each account can have up to 5 keys, each valid for up to one year.
  • Revoke a key or disconnect an app under MCP connections; it stops working within 30 seconds.
  • It's free. If you call it too often you'll be rate-limited briefly, then it recovers on its own. For heavy use, email [email protected].

Data and citation

  • Prices are the median asking price of listings currently for sale, not sold prices. eBay (US), Xianyu (China) and Amazon.co.jp (Japan) are counted separately.
  • Prices update every 6 hours. A round with too few valid listings doesn't publish a price.
  • When you cite the data, credit "VRAMGlass", link back to the relevant page and state the marketplace and date of each price.
  • VRAM and speed figures are planning estimates, not benchmarks. See the methodology.
  • Buy and rental links carry VRAMGlass referral parameters. The price you pay stays the same.

About this repository

This repository holds the documentation and the MCP Registry metadata (server.json) for the hosted VRAMGlass MCP server. The server runs on VRAMGlass infrastructure; its source code is not published here, and there is nothing to install.

The server is listed in the official MCP Registry as com.vramglass/mcp, verified through the vramglass.com domain.

The contents of this repository are licensed under MIT. The hosted service and its data are provided under the VRAMGlass terms, separately from this license.

Source: README.md at commit b443cf3

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 22, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts