NCP - Natural Context Provider (NCP)
NCP - Natural Context Provider (NCP) Details
NCP is a unified MCP platform that consolidates 50+ tools, skills, and Photons into a single, intelligent interface. It enables code-mode execution, on-demand loading, scheduling, and semantic tool discovery, dramatically reducing token usage and latency while enabling AI assistants to work with external MCPs, skills, and Photons. This documentation covers how NCP works, the available MCPs and tools, installation and integration steps for popular clients (Claude Desktop, VS Code, and more), and practical examples that demonstrate how to find, run, and compose tools across MCPs. Whether you’re building with internal MCPs or exploring external tools, NCP provides a scalable, vendor-agnostic foundation for AI-powered automation and tool orchestration.
Use Case
NCP acts as a single entry point to discover and execute tools across multiple MCPs, skills, and Photons. It enables semantic tool discovery with the find command, code-mode execution for composing multi-step TypeScript workflows, and run for executing tools individually. It also supports scheduling, so you can automate recurring tasks. Example usage includes discovering the right tool with find, writing a TypeScript workflow with code that calls tools such as web.search and filesystem read_file, and then scheduling that workflow to run on a schedule. Example from docs: const results = await web.search({ query: "Model Context Protocol conference 2025" }); for (const url of results) { const content = await web.read({ url }); } These patterns show how to integrate external MCPs like filesystem, github, brave-search, and web photon capabilities into a cohesive automation and AI-workflow surface.
Available Tools (14)
Examples & Tutorials
Real example code and usage patterns directly from the documentation:
<h1 class="text-2xl font-semibold mt-5 mb-3">Install NCP</h1>
npm install -g @portel/ncp<h1 class="text-2xl font-semibold mt-5 mb-3">Import existing MCPs (optional)</h1>
ncp config import # Paste your config JSON when prompted<h1 class="text-2xl font-semibold mt-5 mb-3">Configure your MCP client</h1>
{
"mcpServers": {
"ncp": {
"command": "ncp"
}
}
}<h1 class="text-2xl font-semibold mt-5 mb-3">Quick Example: General CLI usage</h1>
<h1 class="text-2xl font-semibold mt-5 mb-3">See your imported MCPs</h1>
ncp list<h1 class="text-2xl font-semibold mt-5 mb-3">Direct testing example from docs</h1>
ncp run filesystem read_file --path "/tmp/test.txt"// A Real Example from the docs
// Search the web for MCP conferences
const results = await web.search({
query: "Model Context Protocol conference 2025"
});// Read each result
for (const url of results) {
const content = await web.read({ url });
// Save to ~/.ncp/mcp-conferences.csv
}
<h1 class="text-2xl font-semibold mt-5 mb-3">Scheduling example from docs</h1>
ncp schedule create code:run "every day at 9am" \
--name "MCP Conference Scraper" \
--catchup-missedInstallation Guide
Step-by-step from the documentation:
1) Install NCP globally
npm install -g @portel/ncp2) Import existing MCPs (optional)
ncp config import # Paste your config JSON when prompted3) Configure your MCP client with a sample config:
{
"mcpServers": {
"ncp": {
"command": "ncp"
}
}
}4) Verify installed tools
ncp listIntegration Guides
Frequently Asked Questions
Is this your MCP?
Claim ownership and get verified badge
Key notes from the docs: - NCP provides a single, unified interface for MCPs, skills, and Photons. - On-demand loading and code-mode execution help reduce token usage and improve responsiveness. - There is an emphasis on vendor-agnostic, plug-and-play MCPs; integrate via the CLI and standard JSON configs. - You can import MCPs, and then configure clients to see only NCP as the tool surface in the AI client.
Node.js 18+ (Node.js 18.x recommended), npm (included with Node.js) or npx for running packages, and command line access (Terminal on Mac/Linux, Command Prompt/PowerShell on Windows).
Compare Alternatives
Similar MCP Tools
6 related toolsAnki MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.
1MCP Agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.
Roundtable AI MCP Server
Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.
MCPJungle
MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.
mcpmcp-server
mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.
Imagen3-MCP
Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.