mcpField
M
Myai

Myai

Local
myaitoken.ioAI & Agents0Updated 23w ago
RepositoryVisit website

About Myai

Myai is an MCP server for accessing decentralized AI inference on the MyAi network. MCP-compatible agents can run model inference and inspect available models, provider nodes, network activity, and MYAI balances.

Key features

  1. 01Run inference through the decentralized network
  2. 02List currently available models
  3. 03Browse provider nodes and hardware
  4. 04View network health and job activity
  5. 05Check MYAI balances and hire a provider

Use cases

  1. 01Summarize a document using an available model
  2. 02Check which providers are online
  3. 03Inspect a provider's hardware before assigning a job
  4. 04Check an address's MYAI token balance

MCP support

The MCP server exposes six tools for inference, network and model discovery, wallet balance checks, and hiring a provider node. MCP clients configure it with an API key or use its automatic free-tier key flow.

#ai#inference#openai-compatible#depin#base#decentralized#myai

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "myai": {
      "command": "uvx",
      "args": [
        "myai-mcp"
      ],
      "env": {
        "MYAI_API_KEY": "<MYAI_API_KEY>",
        "MYAI_BASE_URL": "<MYAI_BASE_URL>"
      }
    }
  }
}
Run commanduvx myai-mcp
Environment variables to set
MYAI_API_KEYSecretRequired for chat/wallet tools; list_models/agents work without
MYAI_BASE_URLOverride only for self-hosted/staging

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimyai-mcp0.2.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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?"

Links

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.