AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Energy › NCP
✦ Free & open sourceEnergy

NCP

Gateway proxy for Model Context Protocol reducing tool context overhead.

Supercharge your AI model context

Manage dozens of Model Context Protocol servers through a single unified gateway.

Free forever · source-available · Elastic-2.0 (source-available, not OSI-approved)
✓ Light setup✓ Browser-based✓ Real-time collaboration
6.6
ZEKAI
Essential MCP gateway
Free & open source · Energy
Ease of setup4
Usefulness8
Maintenance9.5
Community5
★ 100
GITHUB
Oct 2026
UPDATED
Elastic-2.0 (source-available, not OSI-approved)
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Natural Context Provider acts as a single gateway between your AI client and multiple Model Context Protocol servers. It uses on-demand tool discovery, code mode execution, and scheduling to prevent context limit exhaustion. It suits developers and power users juggling multiple MCP servers in clients like Claude Desktop or VS Code.

Runs on
Cross-platform
Hosting
Desktop
Languages
TypeScript
License
Elastic-2.0 (source-available, not OSI-approved)

What it is

NCP consolidates 50+ tool schemas into a small gateway surface featuring find, run, and TypeScript code mode execution. It manages routing, health checks, and response caching behind the scenes while supporting MCP Apps and skills discovery. The tool ensures your assistant stays focused by loading capabilities on demand rather than all at once.

Who it's for

It suits developers and technical professionals running multiple MCP clients like Claude Desktop, Cursor, or VS Code who hit context limits from too many tool schemas. It does not suit non-technical users who expect simple plug-and-play GUI configurations without command line interaction or Node.js prerequisites.

Key features

On-demand tool discovery

Finds tools automatically through a single gateway instead of loading all schemas.

Code mode execution

Allows AI to write and execute multi-step TypeScript workflows directly.

Project-level config

Enables individual projects to define their own MCPs automatically.

Task scheduling

Runs tools and workflows on a schedule within your client environment.

How to start

Up and running in 3 steps

1
Install NCP globally using npm install -g @portel/ncp.
2
Import your existing MCP configurations using the ncp config import command.
3
Add the ncp command runner to your AI client's MCP configuration JSON file.
Real talk

Our honest verdict

What's great

  • Reduces context window waste caused by dozens of simultaneous tool schemas.
  • Supports direct TypeScript execution via code mode for complex workflows.
  • Compatible with major AI clients including Claude Desktop, Cursor, and VS Code.
  • Integrates custom Photons to build TypeScript MCPs without npm publishing.

Where it falls short

  • Requires Node.js 22 or 24 installed on your local machine to run.
  • Requires manual configuration changes in your AI client JSON settings.
  • Adds an abstraction layer that can complicate debugging tool call failures.
Cost

Pricing & license

Free under its Elastic-2.0 licence, with no paid hosted options mentioned in the repository. The only cost is running it yourself on your local machine.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: NCP for Energy
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure NCP for you — and train your team.
Get it done for you ↗
Questions

FAQ

What is the Model Context Protocol?

An open standard by Anthropic that lets AI assistants connect to external tools and data sources like file systems and databases.

Why use NCP instead of connecting MCPs directly?

Connecting many MCPs directly loads all schemas into your AI context at once, causing token exhaustion and confusion, whereas NCP loads tools on demand.

Which AI clients are supported?

It supports Claude Desktop, Claude Code, VS Code, Cursor, Windsurf, Cline, Continue, and other MCP-compatible clients.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Energy — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google