What is AgentPilot?
AgentPilot is a task orchestrator and tool registry with built-in Agent Tool Intelligence. It helps agents find and use the best MCP tools without leaving the agent.

@HMCHENGGH
基本情報
Task orchestrator & tool registry with built-in Agent Tool Intelligence. 28+ MCP tools: task planning, tool search with semantic quality scoring, trust engine, model routing. Find the best MCP tools without leaving your agent.
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": {
"agent-pilot": {
"command": "npx",
"args": [
"-y",
"github:HMCHENGGH/agent-pilot"
]
}
}
}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。
AgentPilot is a task orchestrator and tool registry for MCP (Model Context Protocol) that includes built-in Agent Tool Intelligence. It provides 28+ MCP tools covering task planning, tool search with semantic quality scoring, a trust engine, and model routing.
—
AgentPilot is a task orchestrator and tool registry with built-in Agent Tool Intelligence. It helps agents find and use the best MCP tools without leaving the agent.
AgentPilot offers 28+ MCP tools, including task planning, tool search with semantic quality scoring, a trust engine, and model routing.
The trust engine is one of the 28+ MCP tools provided by AgentPilot. It evaluates tool reliability and quality.
Yes, AgentPilot is designed to let agents find the best MCP tools without leaving the agent environment.
Cartesia MCP is a remote MCP server for Cartesia (https://cartesia.ai) available at https://mcp.cartesia.ai.

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

The AI marketing canvas for Claude and MCP agents. Your agent drafts campaigns as cards on a shared board, briefed by your brand rules, approved by you.
TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
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.
コメント