What runtime and dependencies are required?
Python 3.11+ with libraries: `mcp` (FastMCP), `web3.py`, `httpx`, `click`, `python-dotenv`, and API clients for Zerion, Magic Eden, and Thirdweb.
@Eccentrichealerbuilds
基本情報
This project implements a custom Model Context Protocol (MCP) server designed to work seamlessly with AI-powered IDEs like Cursor and Claude Desktop. It allows users to interact with the Monad Testnet using natural language prompts within their IDE.
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
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。
A custom Model Context Protocol (MCP) server for AI‑powered IDEs like Cursor and Claude Desktop. It allows users to interact with the Monad Testnet using natural language prompts within their editor. The server integrates with Monad Testnet (via web3.py), Zerion API (indexed balances, transactions), Magic Eden API (NFT stats, activity, trends), and Thirdweb Insight API (contract ABIs).
Install and configure according to the SETUP.md instructions. The agent is invoked through natural language prompts in Cursor or Claude Desktop. Required environment variables include THIRDWEB_CLIENT_ID, ZERION_API_KEY, and MAGIC_EDEN_API_KEY (depending on the tools used). No explicit CLI commands are described in the README.
Python 3.11+ with libraries: `mcp` (FastMCP), `web3.py`, `httpx`, `click`, `python-dotenv`, and API clients for Zerion, Magic Eden, and Thirdweb.
It uses the Monad Testnet RPC (direct), Zerion API (balances, transactions), Magic Eden API (NFT stats, activity, trends), and Thirdweb Insight API (contract ABIs). Some tools require the corresponding API key to be set.
Data is sourced live from the Monad Testnet via its RPC endpoint, from indexed data provided by Zerion, from Magic Eden for NFT marketplace information, and from Thirdweb for verified contract metadata.
The server runs as an MCP server and is intended to be connected to by Cursor or Claude Desktop. Authentication is handled via API keys passed as environment variables (`ZERION_API_KEY`, `MAGIC_EDEN_API_KEY`, `THIRDWEB_CLIENT_ID`). No other transports (e.g., HTTP) are mentioned.
The README does not list explicit limitations, but note that the Magic Eden and Zerion tools require valid API keys, and the Thirdweb ABI fetching depends on a client ID. The server is designed for the Monad Testnet only, not for mainnet.
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
コメント