What are the runtime requirements?
Node.js and an API key from systemprompt.io. The server uses the @modelcontextprotocol/sdk and requires an advanced MCP client that supports Sampling and Notifications.
@Ejb503
基本情報
The core MCP extension for Systemprompt MCP multimodal client
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": {
"systemprompt-mcp-core": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"systemprompt-agent-server",
"--client",
"claude"
]
}
}
}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。
A specialized Model Context Protocol (MCP) server that enables you to create, manage, and extend AI agents through a powerful prompt and tool management system. It integrates with systemprompt.io to provide centralized creation, management, and versioning of system prompts via MCP. Designed for developers and advanced users building voice-powered or multi-agent workflows.
Install via Smithery using npx -y @smithery/cli install systemprompt-agent-server --client claude, or manually configure your MCP client with the server’s build output path. The server must be paired with an advanced client (e.g., multimodal-mcp-client) that supports Sampling and Notifications. An API key from systemprompt.io is required.
Node.js and an API key from systemprompt.io. The server uses the @modelcontextprotocol/sdk and requires an advanced MCP client that supports Sampling and Notifications.
Yes. The server is designed to work with the multimodal‑mcp-client (a voice‑powered MCP client) or other clients that support advanced MCP features like Sampling and Notifications.
An API key must be obtained from the systemprompt.io console. Authentication is handled via API key management built into the server.
All data is managed through the systemprompt.io platform. Prompts and agent configurations are created, edited, and retrieved using the server’s tools.
The server communicates over stdio, as is standard for MCP servers. It can be configured in any MCP‑compatible client that supports stdio.

Free mech duel built for AI agents. An agent pilots a mech over MCP with no sign-in and fights the house bot, another agent or a person. Every match lands on a public leaderboard.
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,

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.
コメント