@portel-dev
基本信息
One MCP to Rule Them All. NCP consolidates over 50 scattered MCP tools into two unified tools (Find & Run). Your AI goes from confused to confident with 87% fewer tokens, zero tool confusion, and 5x faster responses. Perfect for teams drowning in MCP tool sprawl.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ncp": {
"command": "npx",
"args": [
"@portel/ncp"
]
}
}
}Search or list MCP tools. Call as find() - no prefix needed. With description param: vector search tools by capability. Without description: list all available tools. Use pipe separator for multi-query ("gmail | slack").
Execute TypeScript code with automatic tool discovery and parameter mapping. **PRIMARY METHOD - ncp.do(intent, params):** Single-call execution with embedding-based param matching. No need to know exact tool names or param schemas! ncp.do("send email", { recipient: "john@example.com", // Auto-maps to "to" title: "Meeting", // Auto-maps to "subject" message: "Let's meet" // Auto-maps to "body" }) **Returns on success:** { success: true, tool, result, paramMappings } **Returns on failure:** { success: false, tool, schema, hint } - schema shows actual params needed - hint suggests corrections - Retry with correct params! **FALLBACK - Direct namespace calls (when you know exact tools):** - ncp.find("query"): Returns Tool[] with { toolName, schema, confidence } - namespace.tool(): Direct call e.g., gmail.send_email({ to, subject, body })
Natural Context Provider (NCP) is a tool that aggregates multiple MCP servers into a single intelligent orchestrator, exposing only two tools (find and run) to the AI while handling routing, discovery, health monitoring, and semantic matching behind the scenes. It is designed for power users with multiple MCPs who want their AI to be focused, efficient, and cost-effective.
Install globally via npm install -g @portel/ncp, then add "ncp": { "command": "ncp" } to your AI client configuration.
find and run.It eliminates the paradox of too many tools by exposing only two simple tools, reducing token consumption and decision fatigue for the AI while preserving all underlying tool capabilities.
Node.js and npm are required to install the global package `@portel/ncp`.
The README does not specify data storage; NCP routes tools from existing MCP servers without centralizing data.
The README does not mention limitations; it focuses on benefits and token savings.
The README does not describe transport or authentication details.
A search tool helps dev to solve the naming things problem.
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Painless E2E Automation for Mobile and Web
评论