Hooks Claude directly into llmctx's condensed Svelte 5 and SvelteKit documentation feeds. The server pulls LLM-optimized markdown from llmctx.com presets, which aggregate and condense official docs into context-friendly formats. Useful when you're coding in Svelte and want your AI assistant to reference current runes syntax, SvelteKit routing patterns, or component APIs without hallucinating outdated pre-v5 idioms. The llmctx service supports combining multiple presets (like svelte,sveltekit) and updates regularly from source repos. Beats copy-pasting docs into prompts or hoping your LLM's training data covers the latest breaking changes from Svelte 4 to 5.
LLM presets and MCP for Svelte 5 and SvelteKit. Visit the site at svelte-llm.stanislav.garden.
This service provides an MCP (Model Context Protocol) endpoint for use with AI assistants:
https://svelte-llm.stanislav.garden/mcp/mcphttps://svelte-llm.stanislav.garden/mcp/sse.env file with the content:
GITHUB_TOKEN=
DB_URL=postgres://admin:admin@localhost:5432/db
public_repo permissions.docker-compose upnvm use
npm i
npm run dev
You can also visit http://localhost:5173/admin to see all the "hidden" endpoints (default password = "secret")
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.
OG image from https://dynamic-og-image-generator.vercel.app/
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent