MCP.so
ログイン

Undesirables Mcp Server

@sailorpepe

Undesirables Mcp Server について

Zero-trust, local-first FastMCP core for The Undesirables. 35+ offline AI agent tools: TCG card grading, conformal risk forecasts (Safe-Hold/Momentum grades), on-chain soul personalities, x402-payable oracle, TTS + 3D forging. No telemetry. BSL 1.1.

基本情報

カテゴリ

その他

ライセンス

NOASSERTION

ランタイム

python

トランスポート

stdio

公開者

sailorpepe

投稿者

Sailor Pepe

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "undesirables": {
      "command": "python3",
      "args": [
        "-m",
        "server"
      ],
      "env": {}
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Undesirables MCP Server?

Undesirables MCP Server is a Python-based server that provides 35+ local compute tools for AI agents with zero cloud dependency. It integrates with Undesirables NFTs to turn them into MCP-compatible AI agents, enabling vision AI card grading, conformal risk forecasting, AI music generation, local image generation, web search, and more. It is designed for developers and AI agents using MCP clients like Claude Desktop or Cursor.

How to use Undesirables MCP Server?

Install via pip install undesirables-mcp-server or clone the repository and set up a virtual environment. Boot the server with python server.py --workspace "/path/to/soul_folder" (requires Ollama running and Python 3.10+). Connect to a chat front-end by configuring an MCP client (e.g., Claude Desktop) with the server command and workspace path.

Key features of Undesirables MCP Server

  • 35+ local compute tools for AI agents
  • Zero cloud dependency; all processing runs locally
  • NFT soul integration for personalized agent behavior
  • Free conformal 30-day price forecast tool
  • On-chain purchase bridge via EVM transaction payload
  • Verified on Glama.ai with 3.8/5 quality score

Use cases of Undesirables MCP Server

  • AI-driven TCG card grading with PSA/Beckett prediction
  • Conformal risk forecasting for financial assets
  • Local image generation and meme creation
  • Persistent RAG memory graphs for personalized agents
  • Zero-token web search and security auditing

FAQ from Undesirables MCP Server

What are the prerequisites for running Undesirables MCP Server?

You need Python 3.10 or higher, Ollama installed and running (the app must be double-clicked and active), and a virtual environment for the server. Optional: a Hugging Face read token for local image generation on Apple Silicon.

How do I connect the server to a chat front-end?

Configure your MCP client (e.g., Claude Desktop) with the server command python server.py --workspace "/path/to/your_soul_folder" and the cwd pointing to the server directory. Restart the client to see the tools.

What if I get an "Ollama connection refused" error?

Make sure Ollama is physically running (the llama icon should appear in your menu bar or system tray). The server requires Ollama to be active for local inference.

Can I use the server without an NFT soul?

The server is designed to work with a soul workspace (downloaded from the Undesirables website). Without a soul folder, the agent may not have a personality or memory; but the core tools (e.g., web search, image generation) may still be available if you provide a workspace path.

What is the license for commercial use?

The project is licensed under BSL-1.1. The README includes a link to the LICENSE file for details.

コメント

「その他」の他のコンテンツ