Svelte Documentation Server

Svelte Documentation Server

Enables vector similarity search and serving of Svelte documentation via the MCP protocol, with support for local caching and multiple llms.txt documentation formats.

spences10

Programming Docs Access
Content Fetching
Visit Server

Tools

search_docs

Search Svelte documentation using specific technical terms and concepts. Returns relevant documentation sections with context. Query Guidelines: - Use technical terms found in documentation (e.g., "route parameters", "state management", "lifecycle hooks") - Search for specific features or concepts rather than asking questions - Include relevant package names for targeted results (e.g., "sveltekit", "stores") Example Queries by Category: 1. Svelte 5 Runes: - "state management runes" (finds $state and state management docs) - "derived state calculation" (locates $derived documentation) - "effect lifecycle runes" (finds $effect usage patterns) - "bindable props svelte" (shows $bindable property usage) 2. Component Patterns: - "component lifecycle" (finds lifecycle documentation) - "event handling svelte5" (shows new event handling patterns) - "component state management" (locates state management docs) - "props typescript definition" (finds prop typing information) 3. SvelteKit Features: - "route parameters sveltekit" (finds routing documentation) - "server routes api" (locates API route docs) - "page data loading" (shows data loading patterns) - "form actions sveltekit" (finds form handling docs) 4. Error Documentation: - "missing export error" (finds specific error docs) - "binding validation errors" (locates validation error info) - "lifecycle hook errors" (shows lifecycle-related errors) - "typescript prop errors" (finds prop typing errors) Query Pattern Examples: ❌ "How do I manage state?" → ✅ "state management runes" ❌ "What are lifecycle hooks?" → ✅ "component lifecycle" ❌ "How do I handle events?" → ✅ "event handling svelte5" ❌ "How do I create dynamic routes?" → ✅ "route parameters sveltekit"

get_next_chunk

Retrieve subsequent chunks of large documents

README

mcp-svelte-docs

A Model Context Protocol (MCP) server that provides efficient access to Svelte documentation with advanced caching, search capabilities, and optimised content delivery. This server integrates directly with Svelte's official documentation, offering both full and compressed variants suitable for different LLM context window sizes.

<a href="https://glama.ai/mcp/servers/wu4hy1xtjb"> <img width="380" height="200" src="https://glama.ai/mcp/servers/wu4hy1xtjb/badge" /> </a>

Features

  • 📚 Complete Svelte documentation access through MCP Resources
  • 🔍 Advanced search capabilities:
    • Document type filtering (API, Tutorial, Example, Error)
    • Section hierarchy awareness
    • Intelligent relevance scoring based on:
      • Term frequency
      • Section importance
      • Document type relevance
      • Exact phrase matching
    • Context-aware result excerpts
    • Related search suggestions
  • 💾 Efficient caching with LibSQL
  • 🔄 Automatic content freshness checks
  • 📦 Support for package-specific documentation (Svelte, Kit, CLI)
  • 📏 Smart content chunking for large documents
  • 🗜️ Compressed variants for smaller context windows
  • 🏗️ Built on the Model Context Protocol

Configuration

This server requires configuration through your MCP client. Here are examples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

{
	"mcpServers": {
		"svelte-docs": {
			"command": "npx",
			"args": ["-y", "mcp-svelte-docs"],
			"env": {
				"LIBSQL_URL": "file:local.db",
				"LIBSQL_AUTH_TOKEN": "your-auth-token-if-using-remote-db"
			}
		}
	}
}

Claude Desktop with WSL Configuration

For WSL environments, add this to your Claude Desktop configuration:

{
	"mcpServers": {
		"svelte-docs": {
			"command": "wsl.exe",
			"args": [
				"bash",
				"-c",
				"LIBSQL_URL=file:local.db LIBSQL_AUTH_TOKEN=your-token npx -y mcp-svelte-docs"
			]
		}
	}
}

Environment Variables

The server supports the following environment variables:

  • LIBSQL_URL (optional): URL for the LibSQL database. Defaults to file:local.db
  • LIBSQL_AUTH_TOKEN (optional): Auth token for remote LibSQL database

API

The server implements both MCP Resources and Tools:

Resources

Access documentation through these URIs:

  • svelte-docs://docs/llms.txt - Documentation index
  • svelte-docs://docs/llms-full.txt - Complete documentation
  • svelte-docs://docs/llms-small.txt - Compressed documentation
  • svelte-docs://docs/{package}/llms.txt - Package-specific documentation
    • Supported packages: svelte, kit, cli

Tools

search_docs

Enhanced search functionality with advanced filtering and context awareness.

Parameters:

  • query (string, required): Search keywords or natural language query
  • doc_type (string, optional): Filter by documentation type
    • Values: 'api', 'tutorial', 'example', 'error', 'all'
    • Default: 'all'
  • context (number, optional): Number of surrounding paragraphs (0-3)
    • Default: 1
  • include_hierarchy (boolean, optional): Include section hierarchy
    • Default: true

Example Usage:

// API Reference Search
{
  "query": "bind:value directive",
  "doc_type": "api",
  "context": 1
}

// Tutorial Search
{
  "query": "routing sveltekit",
  "doc_type": "tutorial",
  "context": 2,
  "include_hierarchy": true
}

get_next_chunk

Retrieve subsequent chunks of large documents.

Parameters:

  • uri (string, required): Document URI
  • chunk_number (number, required): Chunk number to retrieve (1-based)

Development

Setup

  1. Clone the repository
  2. Install dependencies:
pnpm install
  1. Build the project:
pnpm build
  1. Run in development mode:
pnpm dev

Publishing

  1. Update version in package.json
  2. Build the project:
pnpm build
  1. Publish to npm:
pnpm publish

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

Recommended Servers

E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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
Mult Fetch MCP Server

Mult Fetch MCP Server

A versatile MCP-compliant web content fetching tool that supports multiple modes (browser/node), formats (HTML/JSON/Markdown/Text), and intelligent proxy detection, with bilingual interface (English/Chinese).

Featured
Local
Persistent Knowledge Graph

Persistent Knowledge Graph

An implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.

Featured
Local
Hyperbrowser MCP Server

Hyperbrowser MCP Server

Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation. Built specifically for AI developers, it eliminates the headaches of local infrastructure and performance bottlenecks, allowing you to

Featured
Local
Exa MCP

Exa MCP

A Model Context Protocol server that enables AI assistants like Claude to perform real-time web searches using the Exa AI Search API in a safe and controlled manner.

Featured
Web Research Server

Web Research Server

A Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.

Featured
Perplexity Chat MCP Server

Perplexity Chat MCP Server

MCP Server for the Perplexity API.

Featured
Youtube Translate

Youtube Translate

A Model Context Protocol server that enables access to YouTube video content through transcripts, translations, summaries, and subtitle generation in various languages.

Featured
PubMedSearch

PubMedSearch

A Model Content Protocol server that provides tools to search and retrieve academic papers from PubMed database.

Featured