De MCP Server

MCP Server for Data Engineering Knowledge. The de mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 4 defined tools rather than through you.

What it actually does

This repo contains a simple Model Context Protocol (MCP) server built with Node.js and TypeScript. It acts as a "Data Engineering Tutor," providing personalized updates about Data Engineering concepts, patterns, and technologies to a connected AI client.

• Resource (data_engineering_knowledge_memory): — Stores a simple JSON object in data/data-engineering-knowledge.json mapping known concepts (strings) to boolean flags (true)
• de_tutor_read_memory: Reads the current known concepts from the JSON file
• de_tutor_write_memory: Updates the JSON file to mark a concept as known (true) or unknown (false). Takes concept (string) and known (boolean) as input
• de_tutor_get_updates: Uses your OpenRouter API key to query Perplexity (perplexity/sonar-small-online) for recent Data Engineering news, patterns, and technologies
• Prompt (data-engineering-tutor-guidance): — Provides instructions to the connected AI client on how to use the tools in a workflow:

Its toolset

Everything the assistant can do here goes through one of these:

• Tools — **
• de_tutor_read_memory — Reads the current known concepts from the JSON file
• de_tutor_write_memory — Updates the JSON file to mark a concept as known (true) or unknown (false). Takes concept (string) and known (boolean) as input
• de_tutor_get_updates — Uses your OpenRouter API key to query Perplexity (perplexity/sonar-small-online) for recent Data Engineering news, patterns, and technologies

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Configuration

You will need one environment variable: OPENROUTER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• Node.js (v18 or later recommended) - npm (or your preferred Node.js package manager like yarn or pnpm) - An AI client capable of connecting to an MCP server (e.g., Cursor, Claude desktop app) - An OpenRouter API Key (for fetching live Data Engineering updates via Perplexity)

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. De's toolset — Tools, de_tutor_read_memory, de_tutor_write_memory and 1 more — is a fair guide to whether it matches your workflow. It is maintained by scriptstar; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the de mcp server does with a few real requests.