Myai

Created By
myaitoken17 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

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.

Server Config

{
  "mcpServers": {
    "myai": {
      "command": "uvx",
      "args": [
        "myai-mcp"
      ],
      "env": {
        "MYAI_API_KEY": "<OPTIONAL>"
      }
    }
  }
}
Project Info
Created At
17 days ago
Updated At
15 days ago
Author Name
myaitoken
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago