MCP Servers

scratch-mcp

Enables AI agents to programmatically edit Scratch .sb3 projects and preview changes live in TurboWarp Desktop via MCP tools and a live-reload bridge.

README

scratch4js

A pnpm monorepo for working with Scratch .sb3 projects from JavaScript — edit them programmatically, drive them from an AI agent, and preview the results live in TurboWarp Desktop.

Packages

Path	Package	What it is
`packages/scratch4js`	`scratch4js`	The core library: read/edit `.sb3` files with a small, declarative API.
`packages/scratch-mcp`	`scratch-mcp`	An MCP server exposing the library's editing surface as tools, plus a TurboWarp live-reload bridge.
`userscript`	—	Prebuilt TurboWarp Desktop userscript + userstyle that live-reload the project the MCP server edits.

How they fit together

  AI agent / MCP client
          │  (MCP tools over stdio)
          ▼
   ┌──────────────┐   edits in memory   ┌────────────┐
   │  scratch-mcp │ ──────────────────► │ scratch4js │
   └──────┬───────┘   save → .sb3 file  └────────────┘
          │ socket.io bridge (localhost:9060)
          ▼  "loadSB3" → fetch /get.sb3
   TurboWarp Desktop + userscript  ──►  live preview

An agent edits a project through scratch-mcp; on save the server writes the .sb3 and signals the userscript, which reloads it into TurboWarp Desktop instantly.

Getting started

pnpm install
pnpm build          # build every package (scratch4js → dist/)
pnpm lint
pnpm format

Then:

Install the userscript into TurboWarp Desktop (per-OS paths in its README).
Run the MCP server and point your MCP client at it.
Open .sb3 files, edit, and save_project to see changes live.

Workspace layout

.
├── packages/
│   ├── scratch4js/     # the library (+ example_project fixture)
│   └── scratch-mcp/    # the MCP server + live-reload bridge
├── userscript/         # prebuilt TurboWarp Desktop userscript + userstyle
├── pnpm-workspace.yaml
└── package.json        # workspace root (build/lint/format delegate to -r)

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured