@umangbuilds
基本情報
AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions. 11 MCP tools for Claude Desktop, Cursor, and Windsurf. Tri-rail support: x402 (HTTP-native micropayments), MPP (session-based st
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": {
"moltpe": {
"command": "npx",
"args": [
"-y",
"@moltpe/mcp-server"
],
"env": {
"MOLTPE_API_KEY": "<YOUR_API_KEY>"
}
}
}
}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。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
MoltPe is an MCP server implementing payment tools for AI agents, supporting stablecoin micropayments (x402), session-based streaming (MPP), and traditional fiat payment paths. It is a reference implementation for developers building agent payment systems with mock data by default and optional live mode connecting to moltpe.com/mcp for real on-chain transactions.
Install the MCP server with cd mcp-server && npm install && npm start to run on port 3000 with 11 payment tools. Configure with Claude Desktop using the example config in examples/claude-desktop-config.json. For live mode, run PROVIDER_MODE=live MOLTPE_AGENT_TOKEN=swai_... npm start to connect to MoltPe’s production server.
MoltPe is a reference implementation with mock data; for production, developers must implement real PaymentProvider adapters. It shows how agents can pay, get paid, and manage money across different protocols.
Both the mcp-server and x402-client packages have zero runtime dependencies and zero npm audit vulnerabilities.
By default, the server runs with mock data in all three payment providers. In live mode, it connects to moltpe.com/mcp for real on-chain transactions on Polygon and Base.
The project is a reference implementation not intended for production use without custom PaymentProvider adapters. It provides 11 MCP tools and supports three parallel payment paths with a 64-item production deployment checklist available.
The MCP server runs on port 3000 and
GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,
BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
Public docs + tool manifest for the GetIntel MCP connector (app.getintel.ai)
OpenRouter for tools & data — 3,028 APIs for your agent, one token, pay per call. treg.to is a remote MCP server at https://treg.to/mcp/ that gives an agent 3,028 ready-to-call API endpoints across 82 platforms: SEO and
コメント