Gpu Bridge runs on your own machine — the client starts it, so there is no endpoint to ping. 37 installs a week from npm. Last commit 17 Mar 2026.
30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.
Today is the operative word: we check Gpu Bridge every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add gpu-bridge -- npx -y @gpu-bridge/mcp-server
{
"mcpServers": {
"gpu-bridge": {
"args": [
"-y",
"@gpu-bridge/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.gpu-bridge]
command = "npx"
args = ["-y", "@gpu-bridge/mcp-server"]
{
"mcpServers": {
"gpu-bridge": {
"args": [
"-y",
"@gpu-bridge/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gpu-bridge": {
"args": [
"-y",
"@gpu-bridge/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GPUBRIDGE_API_KEY (GPU-Bridge API key (get one at https://gpubridge.io). Starts with gpub_. Optional if using x402 micropayments.).
The author declared them in the registry entry; get the values from the project itself.
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
MCP server for GigaChat — AI chat, embeddings, image generation (Russia)
MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking
MCP server for Forge, Voxell's hosted text-embedding API. Tools: embed and list_models.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Local semantic search — embedding-powered grep for files, zero external services.
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
MCP server for the xAI Grok API — chat, vision, search, and embeddings
Answers built from our own checks of this server.