Taking on 2–3 new engagements in 2026 — EST & PST hours

See how we work →
AI & ML★ 1,428

Npcpy

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

by NPC-Worldwide · NPC-Worldwide/npcpy

How to use Npcpy with Claude

Npcpy is a Model Context Protocol (MCP) server that gives Claude and other AI agents direct access to ai & ml capabilities. Once installed, you can use it in Claude Desktop, Cursor, VS Code with GitHub Copilot, or any MCP-compatible client.

Setup

  1. Clone or install from the GitHub repository
  2. Follow the README for environment setup and credentials
  3. Add the server to your MCP client config (claude_desktop_config.json or .cursor/mcp.json)
  4. Restart your client — Npcpy will appear in the available tools list

About Npcpy

Python★ 1,428 starsUpdated Jul 2026Source: github

Npcpy is an open-source MCP server in the AI & ML category, built in Python. It connects Claude and other MCP-compatible clients to ai & ml systems directly. Source available on GitHub.

Use cases for AI & ML MCP servers

  • Chain AI models and pipelines from a single interface
  • Query model outputs and fine-tuning runs programmatically
  • Automate eval pipelines and benchmark comparisons
  • Connect AI agents to specialized ML infrastructure

Where Npcpy fits in an MCP workflow

Teams use Npcpy to give Claude a direct bridge into ai & ml workflows, so routine actions happen inside the AI client instead of across separate tabs and dashboards.

Npcpy can be connected to MCP clients by following the repository setup instructions, making it useful for teams that want AI access to ai & ml systems.

More AI & ML MCP servers

Built with MCP?

Altor deploys MCP servers into production for B2B engineering teams.

We connect AI agents to your live systems — ClickHouse, Linear, Stripe, GitHub — using MCP and deploy them to production in 3 weeks. Not demo.

Talk to Altor →