OpenBB
Open-source financial data platform for AI agents — consolidates proprietary, licensed, and public data sources
Model Context Protocol servers let agents reach beyond the chat — search your docs, query databases, run code, control your tools. MCP is an open standard, so the same server works across Claude Code, Cursor, Codex, and other MCP clients. Every server listed is verified, with live GitHub data and a plain-English pitch of what it actually does.
Open-source financial data platform for AI agents — consolidates proprietary, licensed, and public data sources
Multi-agent orchestration MCP server for Claude Code — deploys swarms, coordinates workflows, learns from outcomes
MCP server for adaptive web scraping — bypasses anti-bot systems, auto-relocates elements on page changes
MCP server for AI task management — streamlines development workflows with Claude and other AI chats
MCP server for n8n workflow automation — provides AI assistants deep access to 1,500+ n8n nodes and templates
Persistent memory MCP server for AI coding agents — captures, compresses, and reinjects session context
Local knowledge graph MCP server for Claude Code — reduces token costs by providing precise, context-aware code reviews
AI content marketing MCP server — automates content creation, multi-platform publishing, and engagement for creators
MCP server for AI agent context optimization — sandboxes tool output, indexes session events, and retrieves relevant data
MCP server for Claude Code usage — real-time token and cost analysis from local JSONL files
MCP server for semantic code search — indexes your entire codebase for deep context in AI coding agents
MCP server for algorithmic trading — turns natural language into executable strategies, research, and portfolio analysis
MCP server for Claude Code — deep guide on agentic workflows, security, and best practices
MCP server for coding agents — provides isolated, ephemeral container environments for parallel development
MCP server for AI-powered email — self-hosted client with an agent for drafting replies and managing inbox
AI agent orchestration framework — MCP server for autonomous task completion with continuous iteration
Emacs MCP server for Claude Code — deeply integrates AI assistant with Emacs LSP, Tree-sitter, and project tools
MCP server for Claude Code — structural code navigation with 97% token savings and persistent cross-session memory
MCP server for multi-LLM orchestration — unifies OpenAI, Anthropic, Gemini, Groq, DeepSeek, Ollama APIs
MCP server for Claude Code — a project management framework with structured prompts for AI-assisted development
MCP server for token optimization — achieves 95%+ reduction via caching, compression, and smart tool intelligence
MCP server for agent orchestration — manages context, tracks tasks, and automates workflows for coding agents
MCP server for n8n workflows — vectorizes, validates, and manages automation flows
Claude API proxy (MCP server) for rate limit bypass — intelligent load balancing across multiple accounts, real-time analytics
MCP server for Markdown-Driven Task Management — CLI and API for structured dev workflows
Dockerized Claude Code environment — isolated, persistent container with pre-configured Unsplash, Context7, and Playwright MCP servers
Claude Code task runner for complex projects — breaks down tasks, isolates context, and manages execution via MCP server
Local speech-to-text MCP server for Linux — push-to-talk transcription directly into Claude Code via Tmux
A Model Context Protocol (MCP) server exposes tools, data, and prompts to an AI agent through a standard protocol. The server can run locally or remotely; the agent calls its tools as if they were native capabilities.
MCP is an open standard. Claude Code, Cursor, Codex, and a growing list of other agents can all connect to the same MCP server. One implementation, many clients.
Most MCP servers ship as a Node, Python, or Docker package. Add the server to your agent’s MCP config (usually a JSON file with the command, args, and env). Some Claude Code plugins install the server automatically.
Treat any MCP server like any other dependency that runs with your user permissions. Audit the source for popular ones; for unknown ones, run them in a container or sandbox. The MCP spec defines transport (stdio or SSE) but not sandboxing.