About svelte-llm-mcp
svelte-llm-mcp is an MCP server that gives AI assistants access to Svelte 5 and SvelteKit documentation, alongside LLM presets. It is aimed at developers who want assistants to reference Svelte material while coding.
Key features
- 01Access to Svelte 5 and SvelteKit documentation
- 02Streamable HTTP and SSE endpoints
- 03LLM presets provided alongside the server
- 04Debugging setup with MCP Inspector
Use cases
- 01Querying Svelte 5 syntax and usage from an AI assistant
- 02Retrieving reference documentation while building SvelteKit projects
MCP support
The project is an MCP server that exposes Svelte and SvelteKit documentation to MCP clients through Streamable HTTP (/mcp/mcp) and SSE (/mcp/sse) endpoints.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://svelte-llm.stanislav.garden/mcp/mcpclaude mcp add --transport http garden-stanislav-svelte-llm-svelte-llm https://svelte-llm.stanislav.garden/mcp/mcp{"mcpServers":{"garden-stanislav-svelte-llm-svelte-llm":{"type":"http","url":"https://svelte-llm.stanislav.garden/mcp/mcp"}}}Open in Cursor{"servers":{"garden-stanislav-svelte-llm-svelte-llm":{"type":"http","url":"https://svelte-llm.stanislav.garden/mcp/mcp"}}}Open in VS Code{"mcpServers":{"garden-stanislav-svelte-llm-svelte-llm":{"type":"http","url":"https://svelte-llm.stanislav.garden/mcp/mcp"}}}{"mcpServers":{"garden-stanislav-svelte-llm-svelte-llm":{"serverUrl":"https://svelte-llm.stanislav.garden/mcp/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://svelte-llm.stanislav.garden/mcp/mcphttps://svelte-llm.stanislav.garden/mcp/sseTools
2This tool takes no parameters.
Details
From the project READMEsvelte-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/
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.