NCP - Natural Context Provider (NCP)

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.

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.