mcp-documentation-server and mcp-svelte-docs

These are ecosystem siblings: Tool A is a general-purpose MCP documentation server framework with semantic search capabilities, while Tool B is a specialized implementation of that pattern for Svelte-specific documentation access.

mcp-documentation-server
55
Established
mcp-svelte-docs
52
Established
Maintenance 10/25
Adoption 10/25
Maturity 18/25
Community 17/25
Maintenance 13/25
Adoption 10/25
Maturity 18/25
Community 11/25
Stars: 293
Forks: 34
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 124
Forks: 10
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

About mcp-documentation-server

andrea9293/mcp-documentation-server

MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides

Implements the Model Context Protocol (MCP) as a TypeScript server with hybrid search (full-text + vector similarity) powered by the embedded Orama database, eliminating external dependencies. Uses parent-child document chunking with local embeddings via Transformers.js, an LRU cache to avoid recomputing embeddings, and optional Google Gemini integration for AI-powered semantic analysis. Includes an auto-launching web UI dashboard and supports file streaming for large documents without high memory overhead.

About mcp-svelte-docs

spences10/mcp-svelte-docs

🔍 MCP server that lets you search and access Svelte documentation with built-in caching

Extracts TypeScript definitions directly from Svelte 5's source declarations to provide a unified `svelte_definition` tool covering 28+ runes, features, and patterns with three response formats (syntax, quick, full). Integrates with Claude Desktop, Cursor, and Windsurf via MCP, offering fuzzy matching and migration guidance from Svelte 4 to 5 patterns.

Scores updated daily from GitHub, PyPI, and npm data. How scores work