Best Wiki AI Skills & MCP Servers
38 curated Wiki skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Wikimedia Image Search
MCP server enabling AI assistants to search Wikimedia Commons images with metadata and visual previews
Llm Wiki Daemon
Local-first MCP daemon scaffold for the LLM Wiki system.
Kobsidian
TypeScript MCP server for Obsidian with a filesystem-first LLM Wiki layer, Dataview / Canvas / Kanban / Mermaid / Marp / Templates tools, and both stdio and Streamable HTTP transports.
Azure Devops
MCP server for Azure DevOps integration - wikis, work items, pull requests, and variable group read access
Wikipedia
Wikipedia MCP Server
Mediawiki
Model Context Protocol (MCP) server for MediaWiki
Nodemw
MCP server for nodemw - MediaWiki API client
Mediawiki Olioex
Model Context Protocol (MCP) server for MediaWiki
Server Yandex Wiki
MCP Server for Yandex Wiki API integration
Wikipedia
MCP server for Wikipedia API interactions
Flywheel Memory
MCP tools that search, write, and auto-link your Obsidian vault — and learn from your edits.
Server Yandex Wiki
MCP Server for Yandex Wiki API integration. This is a convenience wrapper for @fractalizer/mcp-server-yandex-wiki.
Danbooru Tags
Extract tags from any Danbooru post and explore categories at a glance. Analyze character-specific tag frequencies to surface top traits and clothing patterns. Look up tag and character details from the Danbooru Wiki to add context.
GitHub Wiki Explorer
Navigate and understand GitHub repository documentation effortlessly by retrieving wiki structures and contents. Get direct answers to specific questions about project wikis to save time searching through manual pages. Streamline the onboarding process by quickly grasping the lay
About Wiki skills on iClaude
iClaude is the universal install layer for AI skills. Every Wiki skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.