Myai

@myaitoken

Visit Server

15 days ago

Decentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI. 6 tools (chat, list_models, list_agents, network_stats, wallet_balance, hire_agent). 27+ providers, 22 open models live at https://myaitoken.io.

Overview Tools Comments

Overview

myai-mcp

MCP server for the MyAi decentralized AI inference network.

Gives any MCP-compatible agent (Claude Desktop, Cursor, etc.) access to:

myai_chat — run inference through the decentralized network
myai_list_models — see what models are online right now
myai_list_agents — browse active provider nodes and their hardware
myai_network_stats — live network health and job activity
myai_wallet_balance — check MYAI token balance for any address
myai_hire_agent — pin a job to a specific provider node

Install

uvx myai-mcp

Or with pip:

pip install myai-mcp

Claude Desktop config

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "myai": {
      "command": "uvx",
      "args": ["myai-mcp"],
      "env": {
        "MYAI_API_KEY": "your-api-key-here",
        "MYAI_BASE_URL": "https://api.myaitoken.io"
      }
    }
  }
}

Get an API key at myaitoken.io.

Example usage (once connected)

Ask Claude:

"Use myai_list_models to see what's available, then use myai_chat with qwen2.5-14b to summarize this document."

"Check the MyAi network stats and tell me how many providers are online."

"What's the MYAI balance for 0x454F85B685BBe6C1257b218eE40782d17dFacA9b?"

v0.2.0 — Zero-config

You can now uvx myai-mcp with no env vars. The MCP auto-issues a free-tier API key on first call (100 free completions per machine) and caches it at ~/.myai/key. Set MYAI_API_KEY to use your own key.

Try in Playground

Server Config

{
  "mcpServers": {
    "myai": {
      "command": "uvx",
      "args": [
        "myai-mcp"
      ],
      "env": {
        "MYAI_API_KEY": "<OPTIONAL>"
      }
    }
  }
}

Build with ShipAny.