Model Context Protocol (MCP) Server Directory

AnySearch structured search engine: connect agents to clean, token-efficient Markdown feeds and reduce web scraping token costs by 70%.

OpenMarkdown agent co-edit editor: write markdown alongside Claude Code or Cursor via MCP with local-first storage and instant 0.2-second cold start.

Nitrosend AI email for agents: configure MCP, send campaigns from Claude, and manage deliverability with NitroWheel optimization. Full agent-native email guide.

X MCP server setup: connect Claude and Cursor to Twitter API for posting, searching, and analytics. Compare official vs open-source MCP servers and costs.

ZooData structured JSON extraction: configure MCP, compare token costs vs markdown, and build multi-agent data pipelines with pay-per-field pricing.

Andrej Karpathy's 10 CLAUDE.md rules for Claude Code: think before coding, surgical changes, goal-driven execution. 114.6K GitHub stars. Complete guide with implementation.

OpenAI Codex Micro review: $230 macro pad for agentic coding with 12 programmable keys, OLED display, and haptic feedback. Physical controls for approve, rerun, and manage AI agents.

Superpowers 256K-star agentic skills framework for Claude Code, Codex, and Cursor. Subagent-driven development with 50% fewer tokens and 2x faster delivery. Complete setup guide.

PxPipe image-context proxy cuts Claude Code/Fable 5 token costs 59-70%. Complete setup guide with benchmarks, profitability gate config, and honest limitations.

Aye teachable AI browser pipeline: automate web research with a Chromium browser that learns from corrections. Record Skills, resume checkpoints, and approve sensitive steps. Complete guide with setup, ROI, and limits.

Unabyss cross-LLM memory pipeline: share context across Claude, GPT, and Cursor via MCP. Connect 20+ apps, set granular permissions, and never re-explain yourself. Complete guide with setup, ROI, and honest limits.

LobeHub is the first 'Chief Agent Operator' — hire, schedule, and manage AI agents as a 24/7 team. Complete guide: agent marketplace, fleet scheduling, observability, performance reporting, and honest limitations.