Discover Awesome MCP Servers

Thread Keeper

Multi-agent shared brain MCP server enabling cross-session memory, self-improving skill loops, and inter-agent signaling across Claude, Codex, Gemini, Copilot, and VS Code CLI agents.

Skill Audit MCP

Scans MCP servers, AI agent skills, and plugins for 68+ malicious patterns including credential exfiltration, prompt injection, and code execution.

TradePilot MCP Server

A production-grade MCP server that integrates Polygon.io market data with an 18-layer technical analysis engine to generate actionable options trading signals and high-probability playbooks.

lore-mcp

Architectural memory layer for AI coding. Automatically extracts decisions, detects security gaps, and analyzes git history from your codebase in one command.

SearXNG MCP Server

Enables AI agents to perform privacy-respecting web searches through SearXNG, with support for multiple search engines, categories, and advanced filtering options.

Filo

An unofficial MCP server that gives AI assistants structured access to Italy's Design System .italia, including components, design tokens, usage guidelines, and GitHub issues, updated nightly.

easy-gg-bedwars-mcp

A local-first Python MCP server for Easy.gg BedWars custom scripting, enabling users to create, edit, and sync Roblox BedWars scripts using official APIs and Code Sync.

MCP-DayOne

A Message Control Protocol server that enables Claude Desktop and other applications to interact with Day One journals, allowing automated journal entry creation through a simple API.

liuren

Enables 大六壬 divination by computing the chart (三傳, 四課, etc.) and generating a 天地盤 PNG from a given datetime.

MSSQL MCP Server

A Model Context Protocol server that enables LLMs like Claude to interact with Microsoft SQL Server databases through natural language, supporting queries, data manipulation, and table management.

NEI MCP Server

Enables interaction with the NEI platform to query project resources such as interfaces and business groups. It provides tools for searching by URI or name and supports manual synchronization to ensure local data is up to date.

agentbay-mcp

Persistent memory, teams, and projects for AI agents. 76 MCP tools for storing, recalling, and sharing knowledge across sessions with 4-strategy hybrid search.

Registry Browser MCP

Exposes Registry Browser operations (embed, de-embed, publish, create packages) as MCP tools for AI agents and IDE integrations to manage Unity packages programmatically.

MCP-BPMN Server

Enables AI agents to create, manipulate, and manage BPMN 2.0 diagrams programmatically, with support for Mermaid conversion, auto-layout, and file persistence.

Remote MCP Server (Authless)

Enables deployment of MCP servers on Cloudflare Workers without authentication requirements. Allows users to create custom tools and connect them to MCP clients like Claude Desktop or Cloudflare AI Playground through a remote HTTP endpoint.

MCP-TY

An MCP server leveraging the Rust-based ty type checker to provide AI models with high-performance, semantic Python code analysis and structural navigation. It enables precise symbol searching, cross-file renaming, and diagnostic reporting to improve code understanding and editing accuracy.

token-scout

Discovers LLM models in real time from cloud providers and local Ollama instances, returning compatibility profiles and live pricing so AI agents can route tasks to the cheapest viable model without breaking tool calls or context clipping.

tgfmcp

MCP server that enables Telegram bot interaction via Telegraf, providing tools for sending, replying, reacting, editing, deleting, forwarding messages, and receiving Telegram events over an optional notification channel.

Geo MCP Server

Enables building, querying, and publishing structured knowledge to the decentralized Geo knowledge graph using GRC-20, with tools for graph operations, DAO governance, and file ingestion.

Knowledge MCP Service

Enables AI-powered document analysis and querying for project documentation using vector embeddings stored in Redis. Supports document upload, context-aware Q\&A, automatic test case generation, and requirements traceability through OpenAI integration.

IoT Realm MCP Server 🌐🔌

🌐🔌 An MCP server that exposes real-time sensor data from IoT Realm devices—such as ESP32-based DHT11 clients—to LLMs via the Model Context Protocol. This enables AI agents to access, analyze, and act upon live environmental data.

silentwatch-mcp

An MCP server that surfaces scheduled-job state and detects silent failures (exit 0 but no useful output) for cron, systemd timers, and OpenClaw schedulers, enabling AI agents to query job health and overdue status directly.

Pavan Madduri — Personal Knowledge MCP Server

A Model Context Protocol (MCP) server that exposes a professional profile — certifications, industry articles, open source contributions, and live GitHub activity — as a queryable API for AI agents.

MCP-ChatBot

Tentu, berikut adalah contoh sederhana klien-server MCP (Minecraft Communications Protocol) dalam bahasa Inggris, yang kemudian akan saya terjemahkan ke dalam bahasa Indonesia: **English:** ```python # Simple MCP Client (Python) import socket HOST = '127.0.0.1' # The server's hostname or IP address PORT = 25565 # The port used by the server with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) s.sendall(b'Hello, server!') data = s.recv(1024) print('Received', repr(data)) # Simple MCP Server (Python) import socket HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 25565 # Port to listen on (non-privileged ports are > 1023) with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() conn, addr = s.accept() with conn: print('Connected by', addr) while True: data = conn.recv(1024) if not data: break conn.sendall(data) ``` **Indonesian Translation:** ```python # Contoh Sederhana Klien MCP (Python) import socket HOST = '127.0.0.1' # Alamat IP atau nama host server PORT = 25565 # Port yang digunakan oleh server with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) s.sendall(b'Halo, server!') data = s.recv(1024) print('Diterima', repr(data)) # Contoh Sederhana Server MCP (Python) import socket HOST = '127.0.0.1' # Alamat loopback standar (localhost) PORT = 25565 # Port untuk didengarkan (port non-privilege adalah > 1023) with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() conn, addr = s.accept() with conn: print('Terhubung oleh', addr) while True: data = conn.recv(1024) if not data: break conn.sendall(data) ``` **Explanation (Both Languages):** * **Client:** * Creates a socket and connects to the server's IP address and port. * Sends the message "Hello, server!" to the server. * Receives data back from the server and prints it. * **Server:** * Creates a socket and binds it to the specified IP address and port. * Listens for incoming connections. * Accepts a connection from a client. * Receives data from the client. * Sends the same data back to the client (echo server). * Continues to receive and send data until the client closes the connection. **How to Run:** 1. Save the server code as `server.py` and the client code as `client.py`. 2. Open two terminal windows. 3. In one terminal, run the server: `python server.py` 4. In the other terminal, run the client: `python client.py` You should see the server print "Connected by" and the client print "Received". The client will receive the same message it sent. **Important Notes:** * This is a very basic example. Real MCP communication is much more complex and involves specific packet formats. * This example uses a simple string message. MCP uses binary data. * Error handling is minimal. In a real application, you would need to handle exceptions and potential errors. * The port number (25565) is just an example. You can use any available port above 1023. Minecraft typically uses 25565 by default. * This example is for demonstration purposes only and is not a complete MCP implementation. To work with Minecraft's actual MCP, you would need to understand the packet structure and protocol details. This provides a basic understanding of client-server communication using sockets, which is a fundamental concept behind MCP. Let me know if you have any more questions.

mcp_slack

fetch the latest channels messages chat

Backlogr MCP Server

Enables AI assistants to create and manage development projects with structured backlogs, including tasks, requirements, and progress tracking. Provides a bridge between AI development assistants and project management workflows through standardized MCP tools.

MCP Declarative Server

A utility module for creating Model Context Protocol servers declaratively, allowing developers to easily define tools, prompts, and resources with a simplified syntax.

TMB Bus Arrival Times

Provides real-time bus arrival information for TMB (Transports Metropolitans de Barcelona) bus stops, showing when buses will arrive in minutes with line numbers, destinations, and directions.

Excel MCP Server

Enables AI assistants to read, write, format, and analyze Excel files with 34 tools, including real-time editing on macOS with Microsoft Excel.

EDA Tools MCP Server

A comprehensive Model Context Protocol server that connects AI assistants to Electronic Design Automation tools, enabling Verilog synthesis, simulation, ASIC design flows, and waveform analysis through natural language interaction.