# VRAMGlass MCP server

> Look up GPU and memory asking prices, price history and VRAM figures to plan hardware for local LLMs.

- Listing: https://mcp.tc/i/vramglass
- Connect: use the server's own URL `https://mcp.vramglass.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: VRAMGlass
- Homepage: <https://vramglass.com/docs>
- Docs: <https://vramglass.com/docs>

## About

VRAMGlass provides read-only data on GPUs and memory for running local LLMs: current asking prices, price history, VRAM estimates for models and hardware planning. It tracks listings across markets and lets an assistant answer questions such as what an RTX 4090 costs right now.

The server is hosted at https://mcp.vramglass.com/mcp and uses Streamable HTTP. A free VRAMGlass account is needed. Users can sign in with OAuth through the browser, or pass an API key as a Bearer token in the Authorization header.

## What it can do

- Check current GPU asking prices
- Review GPU price history
- Estimate VRAM needs for models
- Plan hardware for local LLMs
- Compare GPUs by memory and price

## Example prompts

- "What does an RTX 4090 cost right now?"
- "Show the price history of the GeForce RTX 3090."
- "Which GPUs fit a 70B model at Q4 within my budget?"
- "Which GPUs had the biggest price drop in the last 24 hours?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http vramglass https://mcp.vramglass.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **vramglass** and choose **Authenticate**. A browser window opens for the VRAMGlass sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **VRAMGlass** and paste this URL:

```url
https://mcp.vramglass.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when VRAMGlass asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=VRAMGlass&connectorUrl=https%3A%2F%2Fmcp.vramglass.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.vramglass.com/mcp` and click **Add**.

3. Click **Connect** and sign in when VRAMGlass asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://mcp.vramglass.com/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to VRAMGlass to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=vramglass&config=eyJ1cmwiOiJodHRwczovL21jcC52cmFtZ2xhc3MuY29tL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "vramglass": {
      "url": "https://mcp.vramglass.com/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=vramglass&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.vramglass.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"vramglass","type":"http","url":"https://mcp.vramglass.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "vramglass": {
      "type": "http",
      "url": "https://mcp.vramglass.com/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "vramglass": {
      "serverUrl": "https://mcp.vramglass.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add vramglass --url https://mcp.vramglass.com/mcp
codex mcp login vramglass
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.vramglass]
url = "https://mcp.vramglass.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http vramglass https://mcp.vramglass.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth vramglass` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

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

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.vramglass.com/mcp`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-10-28
- Updated: 2026-10-28

---
Source: https://mcp.tc/i/vramglass (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
