Natural Context Provider

v1.5.3Developer Toolsstable

Unified MCP orchestration layer that consolidates multiple MCPs into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by 97% and eliminate choice paralysis.

ai-agentsclaudeclaude-desktopgeminimcp
Share:
90
Stars
0
Downloads
0
Weekly
0/5

What is Natural Context Provider?

Natural Context Provider is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to unified mcp orchestration layer that consolidates multiple mcps into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by ...

Unified MCP orchestration layer that consolidates multiple MCPs into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by 97% and eliminate choice paralysis.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • find
  • code

Use Cases

MCP orchestration and consolidation
Semantic tool discovery and caching
Token usage reduction and choice elimination
portel-dev

Maintainer

LicenseElastic License 2.0
Languagejavascript
Versionv1.5.3
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @portel/ncp

Manual Installation

npx -y @portel/ncp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Natural Context Provider

Natural Context Provider (NCP) is a MCP orchestration meta-server that unifies dozens of MCP servers behind a single semantic interface, cutting token consumption by up to 97% by loading tools on demand rather than all at once. It provides two primary AI-facing tools — 'find' for semantic tool discovery and 'code' for multi-tool TypeScript execution — eliminating the choice paralysis that arises when an AI model sees hundreds of tool definitions simultaneously. Beyond tool aggregation, NCP includes a built-in cron scheduler, dynamic MCP management, a skills system, and usage analytics, making it a complete platform for managing complex multi-MCP agent workflows.

Prerequisites

  • Node.js 18 or higher installed
  • npm available on your PATH for global installation
  • An MCP client such as Claude Desktop, Cursor, OpenAI Agents SDK, or Gemini
  • Optional: existing MCP servers to aggregate under NCP
1

Install NCP globally via npm

Install the @portel/ncp package globally so the 'ncp' CLI command becomes available. Alternatively, use npx to run it without a global install.

npm install -g @portel/ncp
# Or use without installing: npx -y @portel/ncp
2

Import existing MCP configurations

Bring in MCP servers already configured in your MCP clients so NCP can manage and expose them through its unified interface.

ncp config import
3

Configure your MCP client to use NCP

Replace all individual MCP server entries in your client config with a single NCP entry. NCP will handle routing all tool calls to the appropriate underlying servers.

{
  "mcpServers": {
    "ncp": {
      "command": "ncp"
    }
  }
}
4

Enable optional features via settings

Edit ~/.ncp/settings.json or run 'ncp config' to enable the Photon Runtime, scheduler, MCP management, skills, and analytics features.

ncp config
# Or set environment variable:
# NCP_ENABLE_PHOTON_RUNTIME=true
5

Add new MCP servers to NCP

Register additional MCP servers with NCP using the 'ncp add' command. These will become discoverable through NCP's semantic 'find' tool.

ncp add filesystem npx @modelcontextprotocol/server-filesystem ~/Documents
ncp add github npx @modelcontextprotocol/server-github
6

Validate configuration and verify connectivity

Confirm all registered servers are correctly configured and that NCP can reach them.

ncp config validate
ncp list --depth 2

Natural Context Provider Examples

Client configuration

Full claude_desktop_config.json showing NCP as the unified entry point with the Photon Runtime enabled for scheduling and analytics.

{
  "mcpServers": {
    "ncp": {
      "command": "ncp",
      "env": {
        "NCP_ENABLE_PHOTON_RUNTIME": "true"
      }
    }
  }
}

Prompts to try

Prompts that demonstrate NCP's semantic tool discovery, on-demand loading, and scheduling capabilities.

- "Find me a tool that can search GitHub repositories"
- "I need to read a file from disk — what tools do you have for that?"
- "Use code mode to read a file and send its contents in an email in one step"
- "Schedule a daily report generation task at 9am every weekday"
- "Show me which MCP tools I have used most this week"

Troubleshooting Natural Context Provider

'ncp' command not found after global npm install

Check that npm's global bin is on your PATH. Run 'npm config get prefix' to find the prefix directory, then add '<prefix>/bin' to your PATH in your shell profile (.zshrc, .bashrc, etc.).

NCP shows no tools available after configuration

Run 'ncp config import' to sync existing MCP configs, then 'ncp list' to confirm servers are registered. Use 'ncp config validate' to catch misconfigured entries.

Scheduling or analytics tools are missing

These features require the Photon Runtime. Set NCP_ENABLE_PHOTON_RUNTIME=true in the env section of your MCP config, or enable enable_schedule_mcp and enable_analytics_mcp in ~/.ncp/settings.json.

Frequently Asked Questions about Natural Context Provider

What is Natural Context Provider?

Natural Context Provider is a Model Context Protocol (MCP) server that unified mcp orchestration layer that consolidates multiple mcps into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by 97% and eliminate choice paralysis. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Natural Context Provider?

Install via npm with the command: npx -y @portel/ncp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Natural Context Provider?

Natural Context Provider works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Natural Context Provider free to use?

Yes, Natural Context Provider is open source and available under the Elastic License 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ncp-natural-context-provider": { "command": "npx", "args": ["-y", "@portel/ncp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Natural Context Provider?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides