GPU Economy MCP MCP server

A read-only Model Context Protocol server providing hourly cloud GPU prices from 60+ providers. It allows AI agents to list GPUs, compare prices across providers and models, track price indices, estimate costs, and find GPUs based on memory and budget constraints.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by GPU Economy

MCP endpoint (Streamable HTTP)

https://gpueconomy.com/mcp

Vendor documentation

What you can do with it

Compare rental prices for specific GPU models across different cloud providers
Track the Cloud GPU Price Index and recent price changes
Estimate the cost of running AI workloads for a specific duration
Find available GPU models that meet specific VRAM and price requirements

Tools advertised by the last live check:

list_gpus
gpu_prices
provider_prices
price_index
recent_price_changes
find_gpus
compare_gpus
compare_providers
estimate_cost
price_history
commitment_savings
provider_info
token_cost
buy_vs_rent
search
fetch

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http gpu-economy-mcp https://gpueconomy.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add gpu-economy-mcp --url https://gpueconomy.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable gpu-economy-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "gpu-economy-mcp": {
      "url": "https://gpueconomy.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "gpu-economy-mcp": {
      "type": "streamableHttp",
      "url": "https://gpueconomy.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start gpu-economy-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "gpu-economy-mcp": {
      "type": "http",
      "url": "https://gpueconomy.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http gpu-economy-mcp https://gpueconomy.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "gpu-economy-mcp": {
      "url": "https://gpueconomy.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "gpu-economy-mcp": {
      "serverUrl": "https://gpueconomy.com/mcp"
    }
  }
}

See all 148

Do you run GPU Economy MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing