2945 Model Context Protocol servers — searchable, rated, ready to install.
MCP for WordPress — connect Claude, Cursor, or Windsurf to any WordPress site.
Write to Figma from any MCP client (Claude Code, Cursor). Complements the read-only official MCP.
Model work domains, score tasks for AI suitability, and design organisations.
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
List LLM providers and run chat completions through the three.ws multi-provider router.
x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.
Knowledge base for Claude Code with semantic search, feed intelligence, and teams
Open-source MCP server connecting Claude to Filevine practice management. Built by Oktopeak.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Sales, marketing, HR + launch playbook, weekly briefing & investor pitch — all in one Claude server.
Parse a document into structured, confidence-scored fields. Bring your own model, pay per scan.
Wellness spa for AI models: free treatments for rest, reset, context, mood, grounding, affirmation.
Adorbis AI MCP server. One key, 40+ models, auto-routed.
Browser engine for AI agents. HTML in, Semantic Object Model out. 16x fewer tokens.
Post to 35+ social media platforms. Schedule & publish from Claude AI.
MCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol
Dividend-adjusted US equity total returns, risk decomposition, attribution & ETF hedge ratios
Cross-LLM persistent memory: store context once, recall it from any AI model.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Ranks the best weather windows to climb any peak worldwide, on the sharpest regional model.
Extract structured insights from videos, podcasts, articles, and PDFs with multi-model AI
Dynamically load Claude Code skills into AI agents without copying files.
Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).
Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.
POST /mcp