garden.stanislav.svelte-llm/svelte-llm-mcp MCP Server
garden.stanislav.svelte-llm/svelte-llm-mcp
Access Svelte 5 and SvelteKit documentation through an MCP server for AI assistants.
What this kind of tool is for
- Scaffold, lint, or restyle a component your agent is already editing.
- Run accessibility, link, or screenshot checks against a local build.
- Turn a design constraint into generated markup the agent can iterate on.
How to compare servers like this
- Framework fit:
- Check the tool targets your stack (React, Vue, plain HTML) before installing it.
- Runtime needs:
- Some browser-driving tools need a local browser or display; read the setup notes first.
- Maintenance signal:
- Frontend tooling churns quickly; recent commits are a good filter.
- Output quality:
- Prefer tools whose generated code you would accept into the repo as-is.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the garden.stanislav.svelte-llm/svelte-llm-mcp MCP server?
The svelte-llm-mcp server is an MCP (Model Context Protocol) endpoint that provides AI assistants with access to Svelte 5 and SvelteKit documentation. It enables Claude, Cursor, and other AI tools to retrieve and reference official Svelte framework documentation during conversations and code generation.
This MCP server bridges AI assistants with comprehensive Svelte 5 and SvelteKit documentation, allowing you to ask questions about framework features, syntax, and best practices directly within your AI chat or IDE. It's useful for developers building Svelte applications who want AI assistance grounded in official documentation.
How to install garden.stanislav.svelte-llm/svelte-llm-mcp
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"svelte-llm-mcp": {
"url": "https://svelte-llm.stanislav.garden/mcp/mcp"
}
}
}Tools & capabilities
Tools this server exposes to the agent.
Documentation Access— Retrieve Svelte 5 and SvelteKit documentation content for AI assistants
Use cases
- Get AI-assisted answers to Svelte 5 and SvelteKit questions grounded in official docs
- Generate Svelte components with accurate framework knowledge
- Learn SvelteKit routing, stores, and advanced patterns through AI conversation
- Debug Svelte-specific issues with documentation-backed explanations
- Accelerate Svelte development with AI code suggestions informed by framework docs
garden.stanislav.svelte-llm/svelte-llm-mcp MCP server FAQ
It's an MCP endpoint that gives AI assistants like Claude and Cursor access to Svelte 5 and SvelteKit documentation, enabling documentation-grounded assistance for Svelte development.
The public endpoint at svelte-llm.stanislav.garden is available for use. You can also self-host by cloning the repository and running it locally with Docker.
Use the remote endpoint URL: https://svelte-llm.stanislav.garden/mcp/mcp (Streamable HTTP) or https://svelte-llm.stanislav.garden/mcp/sse (SSE for older clients). Configure it in your MCP settings.
The public endpoint requires no authentication. For self-hosting, you'll need a GitHub token with public_repo permissions and a PostgreSQL database.
Yes. Clone the repository, create a .env file with GITHUB_TOKEN and DB_URL, run docker-compose up, then npm install and npm run dev.
The server provides access to Svelte 5 and SvelteKit official documentation for use by AI assistants.
README (reference)
Source of truth, from the repository.
svelte-llm
LLM presets and MCP for Svelte 5 and SvelteKit. Visit the site at svelte-llm.stanislav.garden.
MCP Endpoint
This service provides an MCP (Model Context Protocol) endpoint for use with AI assistants:
- Streamable HTTP (Claude Desktop and most other clients):
https://svelte-llm.stanislav.garden/mcp/mcp - SSE (Older clients that don't support Streamable):
https://svelte-llm.stanislav.garden/mcp/sse
Setup
- Create a
.envfile with the content:GITHUB_TOKEN= DB_URL=postgres://admin:admin@localhost:5432/db - Create a Classic GitHub token. It must have
public_repopermissions. - Enter this in the .env file.
- Run
docker-compose up - Run:
nvm use
npm i
npm run dev
- Run database migrations: visit http://localhost:5173/api/migrate in your browser after starting the dev server.
You can also visit http://localhost:5173/admin to see all the "hidden" endpoints (default password = "secret")
Debug MCP
NODE_TLS_REJECT_UNAUTHORIZED=0 NODE_OPTIONS="--insecure-http-parser" npx @modelcontextprotocol/inspector
You can also use GitHub Copilot in Agent mode to try the agent locally, see .vscode/mcp.json for info on how that works.
Misc
OG image from https://dynamic-og-image-generator.vercel.app/
Related MCP servers
Create, edit, read and review web presentations: slides, linked buttons, pictures, runnable code.
Let Claude and ChatGPT publish real websites — iterate in previews, keep the good one.
Web page or HTML to clean LLM-ready Markdown or JSON. x402 pay-per-call, $0.005, no API key.
Create and edit architecture diagrams from your AI agent; get an SVG and a live editable canvas.
Restaurant management API for meni.ge owners: manage menus, locations, orders, and settings.
Guest API for meni.ge restaurants: browse menus, place orders, reserve tables. No auth needed.