MCP Documentation Server added to readme

[andrea9293]

Description

A TypeScript-based MCP server that provides document management and semantic search capabilities. Upload documents, search them with AI embeddings

Features:
📄 Document Management - Add, list, retrieve, and delete documents with metadata
🔍 Semantic Search - AI-powered search using embeddings
📁 File Upload - Drop .txt/.md/.pdf files in uploads folder for processing
🧩 Smart Chunking - Automatic text splitting for better search accuracy
🗑️ Document Deletion - Clean removal of documents and their chunks
🌍 Multilingual - Supports multiple languages with quality embeddings
💾 Local Storage - All data stored locally in ~/.mcp-documentation-server/ directory
⚡ Fast Setup - No database required, works out of the box

Server Details

• Server:
• Changes to:

Motivation and Context

How many times have you asked cursor or github copilot about new libraries, frameworks, or recent updates only to get outdated or incomplete answers?
My Solution: An MCP server that lets you "feed" fresh, up-to-date documentation directly to your AI through

How Has This Been Tested?

I am a Salesforce architect and all AIs are having trouble with LWC implementation because of syntax, metadata files and more on Salesforce platform. I uploaded Salesforce developer documentation and, I am not hallucinating anymore, the AI ​​can understand the code better and write it.
I also uploaded MCP documentation with full-llms.txt and this was a great help for testing and implementing this same server.

some of my colleagues are also using it and they are finding it very good. tested in vs code and claude desktop

Breaking Changes

classic installation, no changes needed

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• [x ] New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• [x ] Documentation update

Checklist

• [ x] I have read the MCP Protocol Documentation
• [ x] My changes follows MCP security best practices
• [ x] I have updated the server's README accordingly
• [ x] I have tested this with an LLM client
• [ x] My code follows the repository's style guidelines
• [ x] New and existing tests pass locally
• [ x] I have added appropriate error handling
• [ x] I have documented all environment variables and configuration options

Additional context

Set via MCP_EMBEDDING_MODEL environment variable:

Xenova/all-MiniLM-L6-v2 (default) - Fast, good quality
Xenova/paraphrase-multilingual-mpnet-base-v2 (recommended) - Best quality, multilingual but more RAM usage
Important: Changing models requires re-adding all documents as embeddings are incompatible.

[olaservo]

Thanks for your contribution to the servers list. This has been merged in this combined PR: #2143

This is a new process we're trying out, so if you see any issues feel free to re-open the PR and tag me.