MCP Servers

papermc-docs-mcp

Provides local cached access to PaperMC documentation with full-text search, category browsing, and update detection.

README

PaperMC Docs MCP Server

A Model Context Protocol (MCP) server that provides access to PaperMC documentation and Javadocs.

How It Works

This server has two modes:

1. Cached Documentation — Downloads all pages from docs.papermc.io/llms.txt and caches them as markdown files in ~/papermc-docs-mcp/. Each page stores its HTTP ETag for efficient update detection. Tools and resources in this mode operate entirely on the local cache — no network calls at query time.

2. Live Javadocs — Fetches JavaDoc pages on-the-fly from jd.papermc.io. No caching — always up-to-date. Supports version resolution (auto-redirect to latest, partial version matching).

Resources

Cached Documentation

URI Pattern	Description
`papermc-docs://{path}`	Direct access to any cached doc page (e.g. `papermc-docs://paper/dev/getting-started/index.md`)
`papermc-docs://what-is-papermc`	Beginner-friendly introduction to PaperMC

Live Javadocs (no resource — use tools below)

Tools

Cached Documentation Tools

Tool	Description
`list_categories`	List all documentation projects (paper, adventure, velocity, folia, etc.)
`list_docs`	List pages, optionally filtered by category
`search_docs`	Full-text search across all cached pages with ranking and snippets
`refresh_cache`	Download all pages to local cache (needed once on first setup)
`check_updates`	ETag-based per-page update detection across all projects

Live Javadoc Tools

Tool	Description
`list_javadoc_projects`	List all javadoc projects with their latest resolved versions
`resolve_javadoc`	Fetch a class, interface, or package javadoc page (e.g. `org.bukkit.plugin.JavaPlugin`)
`search_javadoc`	Search for classes by name across a project's javadocs

Installation

# Clone and install
git clone https://github.com/SatuSattr/papermc-docs-mcp.git
cd papermc-docs-mcp
npm install

# Optional: download all docs on first run
npm run start:cache

# Start MCP server
npm start

MCP Configuration (opencode.json / claude_desktop_config.json)

{
  "mcpServers": {
    "papermc-docs": {
      "command": "npx",
      "args": ["tsx", "path/to/papermc-docs-mcp/src/index.ts"]
    }
  }
}

Cache Directory

All cached documentation is stored in ~/papermc-docs-mcp/. The --cache flag or refresh_cache tool fills this directory. Once populated, all cached tools and resources work offline.

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

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

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured