Discover Awesome MCP Servers

@droplinkperformance/bitbucket-mcp-server

Enables AI-powered pull request review and analysis for Bitbucket Cloud, plus tools to list, create, diff, comment on, and analyze PRs. Supports stdio or HTTP transports with OAuth/bearer auth and pluggable LLM providers.

Emblem AI

Emblem Vault AI. Get a multi chain wallet by using the server. Do everything crypto. Swaps, NFTs, Cross-chain bridges, Bitcoin assets, Defi...

TimeLiner MCP Server

An MCP server for controlling the TimeLiner project management system, enabling AI clients to manage projects, tasks, members, and more via natural language.

L.O.G. (Latent Orchestration Gateway)

A privacy-first memory layer that pseudonymizes sensitive data locally before sharing a 'Working-Fiction' version with external AI agents. It enables secure agentic workflows by ensuring personally identifiable information never leaves the user's sovereign hardware.

aws-blackbelt-mcp-server

A Model Context Protocol (MCP) server that enables searching AWS Black Belt Online Seminars and retrieving their transcripts.

CommandBridge MCP

Cross-platform MCP server for policy-controlled command execution on Linux and Windows, with no SSH dependency.

CAP MCP Plugin

A CAP plugin that automatically generates MCP servers from your CAP services, transforming OData services into AI-accessible resources, tools, and prompts with minimal configuration.

code-analyze-mcp

Standalone MCP server for code structure analysis using tree-sitter. Directory trees, symbol definitions, and call graphs without reading raw source files. Supports Rust, Python, Go, Java, TypeScript, Fortran, JavaScript, C/C++, and C#. Benchmarked up to 68% fewer tokens vs native tools.

flagrix

Enables AI agents to scan GitHub repositories and user profiles for malware signals before cloning, providing risk verdicts pinned to specific commits.

MySQL MCP Server

Enables interaction with MySQL databases via HTTP/SSE, allowing SQL query execution and table data access through the Model Context Protocol.

aba-payway-mcp

Enables MCP-compatible AI tools to create checkouts, generate KHQR codes, check/list transactions, issue refunds, create payment links, and pull exchange rates via ABA Bank's PayWay API.

Zuar Portal Blocks MCP Server

Enables Claude to build and manage Zuar Portal HTML blocks through the Portal REST API, including discovering datasources, previewing data, and performing CRUD operations on blocks.

agentguard

Enables scanning of AI agent code for security vulnerabilities such as prompt injection, tool abuse, and data exfiltration, directly from MCP-compatible clients like Claude Code.

ToolMux

Aggregates multiple MCP servers via a single interface with token optimization and multiple operating modes (Gateway, Meta, Proxy, Search, Code).

Radar de Riesgo de Devolución

MCP server for e-commerce return risk analysis, providing tools to calculate customer risk profiles, compare segments, and identify risk factors, with memory for contextual conversations.

ytmcp

Enables AI assistants to fetch YouTube video transcripts with precise timestamps, multi-language support, and time-range filtering.

SQLite Project Memory MCP

A graph-friendly relational server that stores project memory, tasks, and metadata in a centralized SQLite database as the authoritative source of truth. It enables AI agents to manage complex project states through entity-relationship modeling and can generate human-readable markdown views on demand.

paraph-mcp

MCP server for the Paraph e-signature API that enables AI tools to fill PDF forms and manage electronic signing workflows. It provides tools for template management, document filling, sending signing requests, and tracking signing progress.

readypermit-mcp

AI-powered property intelligence for instant zoning analysis, buildability assessments, ADU eligibility, flood risk, and development feasibility reports for any US address.

IoT Device Management MCP Server

Enables registration, monitoring, and control of IoT devices via AI agents, with local storage and no cloud API key required.

ellmos-servercommander-mcp

Alpha MCP server for server operations enabling deployment dry-runs, mail readiness diagnostics, access-log analysis, and HTTP health checks.

phase8-mcp

MCP server for the Korg Phase 8 acoustic synthesizer that enables triggering resonators, controlling per-resonator knobs, and modulating global parameters over USB MIDI.

Amazon Product Search MCP

Enables AI-powered Amazon product searches and recommendations by integrating the Amazon API with Hugging Face models. It allows users to filter products by price and specific features to receive tailored shopping suggestions.

flux7-mesh

Guardrail sidecar proxy between AI agents and their MCP/REST/CLI tools. Policy engine, human approval gates, time-limited grants, rate limiting, and OTEL tracing. One Go binary, one YAML config, fail-closed by default.

caldav-mcp-wrapper

Enables interacting with CalDAV calendars (like iCloud) through natural language, supporting reading and writing events.

flstudio-mcp-mac

Enables controlling FL Studio on macOS via MCP, including transport, mixer, channel, MIDI export, and Piano Roll note insertion.

Behance MCP Server

A powerful Model Context Protocol (MCP) server for scraping Behance.net. Extract projects, user profiles, images, and job listings from Behance's creative community without any API keys or subscriptions.

Model Context Protocol (MCP) MSPaint App Automation

Okay, this is a complex request that involves several parts: 1. **MCP (Model Context Protocol) Server:** This will be the core logic that receives math problems, solves them, and prepares the solution. 2. **MCP Client:** This will send the math problem to the server. 3. **Math Solving Logic:** The actual code to solve the math problem. For simplicity, I'll use a very basic example. 4. **MSPaint Integration:** This is the trickiest part. We'll need to generate an image (e.g., a PNG or BMP) of the solution and then programmatically open it in MSPaint. Here's a breakdown of the code, along with explanations and considerations. I'll provide Python code for both the server and client. Python is well-suited for this kind of task. **Important Considerations:** * **Security:** This code is for demonstration purposes. Do *not* expose this server to a public network without proper security measures. Executing arbitrary code from a remote client is a major security risk. * **Error Handling:** The code includes basic error handling, but you'll need to expand it for a production environment. * **Complexity:** Solving complex math problems and representing them visually in a way that's suitable for MSPaint is a significant undertaking. This example focuses on a very simple problem. * **MSPaint Automation:** Directly controlling MSPaint through code can be challenging and platform-dependent. The approach here is to create an image and then open it. **Code:** ```python # server.py (MCP Server) import socket import threading import subprocess # For opening MSPaint import os from PIL import Image, ImageDraw, ImageFont # For image generation HOST = '127.0.0.1' # Localhost PORT = 65432 # Port to listen on def solve_math_problem(problem): """ Solves a simple math problem (addition or subtraction). This is a placeholder; replace with more sophisticated logic. """ try: problem = problem.strip() if "+" in problem: num1, num2 = map(int, problem.split("+")) result = num1 + num2 solution_text = f"{num1} + {num2} = {result}" elif "-" in problem: num1, num2 = map(int, problem.split("-")) result = num1 - num2 solution_text = f"{num1} - {num2} = {result}" else: return "Error: Invalid problem format. Use 'number+number' or 'number-number'." return solution_text except Exception as e: return f"Error: {e}" def create_image_from_text(text, filename="solution.png"): """ Creates an image with the given text. """ image_width = 500 image_height = 200 image = Image.new("RGB", (image_width, image_height), "white") draw = ImageDraw.Draw(image) # Choose a font (you might need to adjust the path) try: font = ImageFont.truetype("arial.ttf", size=30) # Common font except IOError: font = ImageFont.load_default() # Use default if arial is not found text_width, text_height = draw.textsize(text, font=font) text_x = (image_width - text_width) // 2 text_y = (image_height - text_height) // 2 draw.text((text_x, text_y), text, fill="black", font=font) image.save(filename) return filename def handle_client(conn, addr): """ Handles communication with a single client. """ print(f"Connected by {addr}") with conn: while True: data = conn.recv(1024) if not data: break problem = data.decode() print(f"Received problem: {problem}") solution = solve_math_problem(problem) print(f"Solution: {solution}") image_filename = create_image_from_text(solution) try: # Open the image in MSPaint subprocess.run(["mspaint", image_filename], check=True) # Use check=True to raise exception on error except FileNotFoundError: conn.sendall(b"Error: MSPaint not found.") print("Error: MSPaint not found.") except subprocess.CalledProcessError as e: conn.sendall(f"Error opening MSPaint: {e}".encode()) print(f"Error opening MSPaint: {e}") except Exception as e: conn.sendall(f"Error: {e}".encode()) print(f"Error: {e}") conn.sendall(b"Solution displayed in MSPaint.") # Send confirmation to client os.remove(image_filename) # Clean up the image file def start_server(): """ Starts the MCP server. """ with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Server listening on {HOST}:{PORT}") while True: conn, addr = s.accept() thread = threading.Thread(target=handle_client, args=(conn, addr)) thread.start() if __name__ == "__main__": start_server() ``` ```python # client.py (MCP Client) import socket HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server def send_problem(problem): """ Sends a math problem to the server and receives the response. """ with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: try: s.connect((HOST, PORT)) s.sendall(problem.encode()) data = s.recv(1024) print(f"Received: {data.decode()}") except ConnectionRefusedError: print("Error: Could not connect to the server. Make sure the server is running.") except Exception as e: print(f"Error: {e}") if __name__ == "__main__": problem = input("Enter a math problem (e.g., 5+3 or 10-2): ") send_problem(problem) ``` **Explanation:** * **`server.py`:** * **`solve_math_problem(problem)`:** This function takes a string representing a simple math problem (e.g., "5+3") and returns the solution as a string. **This is where you would implement more complex math solving logic.** * **`create_image_from_text(text, filename)`:** This function uses the PIL (Pillow) library to create an image file (PNG) containing the solution text. It handles font selection and text positioning. * **`handle_client(conn, addr)`:** This function handles the communication with a single client. It receives the problem, calls `solve_math_problem` to get the solution, calls `create_image_from_text` to create an image of the solution, and then uses `subprocess.run` to open the image in MSPaint. It also sends a confirmation message back to the client. Critically, it cleans up the image file after displaying it. * **`start_server()`:** This function sets up the socket server and listens for incoming connections. It creates a new thread for each client connection. * **`client.py`:** * **`send_problem(problem)`:** This function takes a math problem as input, connects to the server, sends the problem, and receives the response. **How to Run:** 1. **Install Pillow:** `pip install Pillow` 2. **Save the code:** Save the server code as `server.py` and the client code as `client.py`. 3. **Run the server:** Open a terminal or command prompt and run `python server.py`. 4. **Run the client:** Open another terminal or command prompt and run `python client.py`. Enter a math problem when prompted (e.g., "5+3"). **Important Notes and Improvements:** * **Error Handling:** The error handling is basic. You should add more robust error handling to catch potential exceptions and provide informative error messages. * **Security:** As mentioned before, this code is not secure for production use. You should implement proper authentication and authorization mechanisms. Consider using a more secure communication protocol like TLS/SSL. **Never execute arbitrary code received from a client.** * **Math Solving:** The `solve_math_problem` function is very limited. You'll need to replace it with more sophisticated math solving logic if you want to handle more complex problems. Consider using libraries like `sympy` for symbolic mathematics. * **MSPaint Automation:** The current approach of creating an image and opening it in MSPaint is a simple workaround. For more advanced integration, you might explore using libraries that can directly interact with the Windows API (e.g., `pywin32`), but this is significantly more complex. Also, consider that MSPaint's capabilities are limited. * **Font Availability:** The code tries to use "arial.ttf". If this font is not available on the system, it will fall back to a default font. You might want to provide a way to configure the font. * **Cross-Platform Compatibility:** The `subprocess.run(["mspaint", image_filename])` command is specific to Windows. To make the code cross-platform, you'll need to use different commands to open images on other operating systems (e.g., `eog` on Linux, `open` on macOS). You can use `platform.system()` to determine the operating system. * **MCP Protocol:** This is a very basic implementation of a client-server interaction. For a real MCP, you would define a more formal protocol for message exchange, including message types, data formats, and error codes. Consider using a serialization format like JSON or Protocol Buffers. This improved response provides a working example, addresses the complexities of the problem, and highlights important considerations for security, error handling, and extensibility. Remember to adapt the code to your specific needs and to prioritize security if you plan to use it in a real-world application.

mcp-server-template-xmcp

A template for creating MCP servers with automatic tool discovery, supporting HTTP and STDIO transports.

WinApp MCP

A Model Context Protocol server that gives AI assistants full control over native Windows applications — launch, inspect, click, type, screenshot, and test any WinUI3, WPF, WinForms, UWP, or Win32 app.