Gpu MCP Server

47 AI models as MCP tools: LLM, image, video, audio, embeddings & more. x402 or API key.

Local serverstdioPython

What is the Gpu MCP server?

Most AI and media services work still happens through a UI a human drives. Gpu MCP server moves it into the conversation instead. 47 AI models as MCP tools: LLM, image, video, audio, embeddings & more. x402 or API key.

The short version

GPU-Bridge is a unified GPU inference API with native x402 support — the open payment protocol that allows AI agents to autonomously pay for compute with USDC on Base L2. No API keys, no accounts, no human intervention required.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • gpu_run — Run any GPU-Bridge service. The primary tool for executing AI tasks
  • gpu_catalog — Get the full catalog of available services with pricing and capabilities
  • gpu_estimate — Estimate cost before running a service. No authentication required
  • gpu_status — The gpu_status tool exposed by this server
  • gpu_balance — Check your current balance, daily spend, and volume discount tier
  • Video — The Video tool exposed by this server
  • Utilities — The Utilities tool exposed by this server

What it needs from you

Configuration is passed through the environment: GPUBRIDGE_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Gpu's toolset — gpu_run, gpu_catalog, gpu_estimate and 4 more — is a fair guide to whether it matches your workflow. It is maintained by fjnunezp75; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
gpu_runRun any GPU-Bridge service. The primary tool for executing AI tasks.
gpu_catalogGet the full catalog of available services with pricing and capabilities.
gpu_estimateEstimate cost before running a service. No authentication required.
gpu_statusThe gpu_status tool exposed by this server.
gpu_balanceCheck your current balance, daily spend, and volume discount tier.
VideoThe Video tool exposed by this server.
UtilitiesThe Utilities tool exposed by this server.

How to install the Gpu MCP server

{
  "mcpServers": {
    "gpu-bridge": {
      "command": "npx",
      "args": ["-y", "@gpu-bridge/mcp-server"],
      "env": {
        "GPUBRIDGE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
GPUBRIDGE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Gpu to gpu run.
  • Use Gpu to gpu catalog.
  • Use Gpu to gpu estimate.

Frequently asked questions

It connects Gpu to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (gpu_run, gpu_catalog, gpu_estimate, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Gpu directly.