GlianaAI runs on your own machine — the client starts it, so there is no endpoint to ping. 325 installs a week from npm. Last commit 29 Oct 2026.
Pay-per-call AI: 59 generative models (image, video, music, speech). No signup, no API key.
Today is the operative word: we check GlianaAI 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 gliana-ai-mcp -- npx -y gliana-ai-mcp
{
"mcpServers": {
"gliana-ai-mcp": {
"command": "npx",
"args": [
"-y",
"gliana-ai-mcp"
]
}
}
}
[mcp_servers.gliana-ai-mcp]
command = "npx"
args = ["-y", "gliana-ai-mcp"]
{
"mcpServers": {
"gliana-ai-mcp": {
"command": "npx",
"args": [
"-y",
"gliana-ai-mcp"
]
}
}
}
{
"servers": {
"gliana-ai-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gliana-ai-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
GLIANA_WALLET_KEY (0x EVM private key for a wallet holding USDC on Base/Tempo — enables the paid generate tool. Discovery tools work without it), GLIANA_SOLANA_KEY (Solana secret key (base58 or JSON array) — enables paying with the solana rail), GLIANA_RAIL (Payment rail for generate: base | tempo | solana (default base)), GLIANA_API_URL (Override the gateway base URL (default https://api.glianalabs.com)).
Generate images, video, speech, music and text with HiAPI's AI models. OAuth or API key.
One API for 100+ AI video, image, music and speech models.
Ask other AI models and generate images, speech, music and video from your coding agent.
Generate video, images, speech and music with 120+ AI models and render TSX videos to MP4
Generate images, video, music, speech, 3D, logos and product shots with 60+ AI models.
Generate images, video, speech and music, and run LLM chat, across 10,000+ models on ModelsLab.
AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.
Generate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google models
Answers built from our own checks of this server.