Best Markdown AI Skills & MCP Servers

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

MCP server that makes remote markdown files available as mcp resources

Comprehensive HTTP fetch MCP server: SSRF protection, HTML-to-markdown, reader-mode, metadata / link / sitemap / RSS-Atom extraction, robots.txt verdicts

Pay-per-fetch MCP server. Agent wallet pays $0.005 USDC on Base (or XRP on XRPL Mainnet) per call via the x402 protocol. Returns clean markdown. No accounts, no API keys, no humans in the loop.

Agent-optimized MCP server for extracting clean, structured content from web pages - built specifically for AI agents that need LLM-friendly web data

Websites from Markdown. Built for AI coding assistants.

MCP server for Misar.Blog — publish blog posts, manage drafts, generate AI cover images, and access analytics from Claude Code, Cursor & Windsurf.

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP in

Format data into various output formats — pretty JSON, YAML, markdown, ASCII tables.

Universal Skills MCP Server — load Markdown skills from arbitrary folders, lazy-by-design, cross-tool (Claude Code / Codex CLI / any MCP client).

An MCP server that fetches web pages and converts them to clean, readable Markdown.

MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati

MCP tools that search, write, and auto-link your Obsidian vault — and learn from your edits.

Markdown Content Preprocessor - Fetch web pages, extract content, convert to clean Markdown

DollhouseMCP - A Model Context Protocol (MCP) server that enables dynamic AI persona management from markdown files, allowing Claude and other compatible AI assistants to activate and switch between different behavioral personas.

The web data platform for AI agents — fetch, search, crawl, extract, monitor, screenshot. 55+ domain extractors, 65-98% token savings, MCP server included. One API call.

MCP server: fetch a URL, return clean markdown. Built for AI agents.

Opinionated MCP for Bear Notes. Relevance-ranked search across titles, bodies, hierarchical tags. Offline-first.

MCP server for markdown plan review — companion to the MD Feedback VS Code extension. AI agents read annotations, mark tasks done, evaluate quality gates, and generate session handoffs. 27 tools for Claude Code, Cursor, and other MCP-compatible clients.

Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

Turn Claude research output into designed PDFs. Cover page, table of contents, code blocks that hold across pages. MCP server and Claude Code skill for markdown to PDF.

Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.

Thunderbit MCP Server — AI-powered web scraping and structured data extraction for Claude, ChatGPT, and other MCP-compatible AI assistants.