Discover Awesome MCP Servers

Dynamics 365 MCP Server by CData

Dynamics 365 MCP Server by CData

mcp-plots

A MCP server for data visualization. It exposes tools to render charts (line, bar, pie, scatter, heatmap, etc.) from data and returns plots as either image/text/mermaid diagram.

bizdays

Provides deterministic business-day calculations for AI agents, correctly handling country-specific weekends and public holidays.

@leonardocrdso/clean-code-mcp

An MCP server that provides 63 Clean Code principles for AI-assisted code review and development.

material-icons-agent-skill

Enables AI agents to search, import, migrate, validate, and maintain official Google Material Symbols across various platforms and IDEs.

DeepSeek MCP Server

Okay, here's a basic outline and code snippet for a simple MCP (Minecraft Protocol) server in Go that redirects questions to Deepseek models. This is a starting point and will require significant expansion to be fully functional. **Important Considerations:** * **Minecraft Protocol Complexity:** The Minecraft protocol is complex. This example handles a very basic handshake and chat message. You'll need to implement more of the protocol to handle player connections, world data, etc. Libraries like `go-mc` can help. * **Deepseek API Integration:** You'll need to obtain an API key from Deepseek and integrate their API into the `handleChatMessage` function. The example uses a placeholder. * **Error Handling:** The code includes basic error handling, but you should add more robust error handling and logging. * **Security:** This is a very basic example and doesn't include any security measures. You should add appropriate security measures, such as authentication and authorization, before deploying this server. * **Performance:** Consider using goroutines and channels to handle multiple connections concurrently. * **Dependencies:** You'll need to install the `go-mc` library. **Code (main.go):** ```go package main import ( "bufio" "encoding/json" "fmt" "log" "net" "os" "strings" "github.com/Tnze/go-mc/net/packet" ) const ( serverAddress = "0.0.0.0:25565" // Listen on all interfaces, port 25565 deepseekAPIEndpoint = "YOUR_DEEPSEEK_API_ENDPOINT" // Replace with your Deepseek API endpoint deepseekAPIKey = "YOUR_DEEPSEEK_API_KEY" // Replace with your Deepseek API key ) func main() { listener, err := net.Listen("tcp", serverAddress) if err != nil { log.Fatalf("Failed to listen: %v", err) } defer listener.Close() fmt.Printf("Server listening on %s\n", serverAddress) for { conn, err := listener.Accept() if err != nil { log.Printf("Failed to accept connection: %v", err) continue } go handleConnection(conn) } } func handleConnection(conn net.Conn) { defer conn.Close() fmt.Printf("Accepted connection from %s\n", conn.RemoteAddr()) // Handle Handshake and Status (very basic) if err := handleHandshake(conn); err != nil { log.Printf("Handshake error: %v", err) return } // Main loop to read messages reader := bufio.NewReader(conn) for { message, err := reader.ReadString('\n') if err != nil { log.Printf("Error reading message: %v", err) return } message = strings.TrimSpace(message) if message == "" { continue // Ignore empty messages } fmt.Printf("Received message: %s\n", message) response, err := handleChatMessage(message) if err != nil { log.Printf("Error processing message: %v", err) response = "Error processing your request." } // Send the response back to the client _, err = conn.Write([]byte(response + "\n")) // Minecraft uses \n as a delimiter if err != nil { log.Printf("Error sending response: %v", err) return } } } func handleHandshake(conn net.Conn) error { // Read the handshake packet var p packet.Packet if _, err := p.ReadFrom(conn); err != nil { return fmt.Errorf("read handshake packet: %w", err) } var protocolVersion int32 var serverAddress string var serverPort uint16 var nextState int32 if err := p.Scan( &protocolVersion, &serverAddress, &serverPort, &nextState, ); err != nil { return fmt.Errorf("scan handshake packet: %w", err) } fmt.Printf("Protocol Version: %d, Server Address: %s, Server Port: %d, Next State: %d\n", protocolVersion, serverAddress, serverPort, nextState) // You might want to validate the protocol version here // Respond to the client based on the next state switch nextState { case 1: // Status // Respond with server status (e.g., player count, MOTD) statusResponse := `{ "version": { "name": "Go-Deepseek-Bridge", "protocol": 757 }, "players": { "max": 100, "online": 0, "sample": [] }, "description": { "text": "A Minecraft server powered by Deepseek!" } }` // Write the length of the JSON string as a VarInt var statusPacket packet.Packet statusPacket.ID = 0x00 // Status Response packet ID statusPacket.Data = []byte(statusResponse) if _, err := statusPacket.WriteTo(conn); err != nil { return fmt.Errorf("write status response: %w", err) } // Handle Ping if _, err := p.ReadFrom(conn); err != nil { return fmt.Errorf("read ping packet: %w", err) } var payload int64 if err := p.Scan(&payload); err != nil { return fmt.Errorf("scan ping packet: %w", err) } // Respond with the same payload var pongPacket packet.Packet pongPacket.ID = 0x01 // Pong packet ID pongPacket.Data = packet.Pack(payload) if _, err := pongPacket.WriteTo(conn); err != nil { return fmt.Errorf("write pong response: %w", err) } return nil case 2: // Login // Handle login process (e.g., authentication) // For simplicity, we'll just accept the connection var loginStartPacket packet.Packet if _, err := loginStartPacket.ReadFrom(conn); err != nil { return fmt.Errorf("read login start packet: %w", err) } var username string if err := loginStartPacket.Scan(&username); err != nil { return fmt.Errorf("scan login start packet: %w", err) } fmt.Printf("Player %s is trying to log in\n", username) // Send Login Success packet loginSuccess := map[string]interface{}{ "uuid": "00000000-0000-0000-0000-000000000000", // Dummy UUID "username": username, } loginSuccessJSON, err := json.Marshal(loginSuccess) if err != nil { return fmt.Errorf("marshal login success json: %w", err) } var loginSuccessPacket packet.Packet loginSuccessPacket.ID = 0x02 // Login Success packet ID loginSuccessPacket.Data = loginSuccessJSON if _, err := loginSuccessPacket.WriteTo(conn); err != nil { return fmt.Errorf("write login success packet: %w", err) } return nil default: return fmt.Errorf("unknown next state: %d", nextState) } } func handleChatMessage(message string) (string, error) { // **Replace this with your Deepseek API call** // Example: // response, err := callDeepseekAPI(message) // if err != nil { // return "", err // } // return response, nil // Placeholder response return fmt.Sprintf("Deepseek says: You asked: %s", message), nil } // Placeholder for Deepseek API call func callDeepseekAPI(message string) (string, error) { // Implement your Deepseek API call here // Use the deepseekAPIEndpoint and deepseekAPIKey constants // Example using os.Getenv (for API key security): // apiKey := os.Getenv("DEEPSEEK_API_KEY") // if apiKey == "" { // return "", fmt.Errorf("DEEPSEEK_API_KEY environment variable not set") // } // This is just a placeholder. You'll need to use an HTTP client // (e.g., net/http) to make a request to the Deepseek API. return fmt.Sprintf("Deepseek API (placeholder) says: Processing: %s", message), nil } ``` **To run this code:** 1. **Install Go:** Make sure you have Go installed. 2. **Install go-mc:** `go get github.com/Tnze/go-mc/net/packet` 3. **Replace Placeholders:** Fill in the `deepseekAPIEndpoint` and `deepseekAPIKey` constants with your actual Deepseek API credentials. **Do not commit your API key directly to your code repository!** Use environment variables or a configuration file. 4. **Run the server:** `go run main.go` 5. **Connect with Minecraft:** Start your Minecraft client and connect to `localhost:25565`. **Explanation:** 1. **`main` Function:** * Sets up a TCP listener on port 25565. * Accepts incoming connections in a loop. * Spawns a goroutine for each connection to handle it concurrently. 2. **`handleConnection` Function:** * Handles a single client connection. * Reads messages from the client. * Calls `handleChatMessage` to process the message and get a response from Deepseek (placeholder). * Sends the response back to the client. 3. **`handleHandshake` Function:** * Handles the initial handshake process of the Minecraft protocol. * Reads the handshake packet. * Parses the protocol version, server address, port, and next state. * Responds to the client based on the next state: * **Status (1):** Sends a server status response (MOTD, player count). * **Login (2):** Handles the login process (very basic, just accepts the connection). 4. **`handleChatMessage` Function:** * This is where you'll integrate with the Deepseek API. * Currently, it's a placeholder that simply returns a message indicating that Deepseek is processing the request. * **You need to replace this with your actual Deepseek API call.** 5. **`callDeepseekAPI` Function:** * A placeholder function that shows where you would make the HTTP request to the Deepseek API. * **You need to implement the actual API call here.** Use the `net/http` package to make the request. Remember to handle errors and parse the JSON response from Deepseek. **Next Steps:** 1. **Implement Deepseek API Integration:** Replace the placeholder in `handleChatMessage` and `callDeepseekAPI` with your actual Deepseek API call. Use the `net/http` package to make the request, handle errors, and parse the JSON response. 2. **Implement More of the Minecraft Protocol:** This example only handles a very basic handshake and chat message. You'll need to implement more of the protocol to handle player movement, world data, etc. Consider using a library like `go-mc` to simplify this. 3. **Error Handling:** Add more robust error handling and logging. 4. **Security:** Add appropriate security measures, such as authentication and authorization. 5. **Configuration:** Use environment variables or a configuration file to store sensitive information like API keys. 6. **Concurrency:** Use goroutines and channels to handle multiple connections concurrently. 7. **Testing:** Thoroughly test your server with a Minecraft client. **Example Deepseek API Call (Conceptual):** ```go import ( "bytes" "encoding/json" "fmt" "net/http" "os" ) func callDeepseekAPI(message string) (string, error) { apiKey := os.Getenv("DEEPSEEK_API_KEY") if apiKey == "" { return "", fmt.Errorf("DEEPSEEK_API_KEY environment variable not set") } requestBody, err := json.Marshal(map[string]string{ "prompt": message, }) if err != nil { return "", fmt.Errorf("marshal request body: %w", err) } req, err := http.NewRequest("POST", deepseekAPIEndpoint, bytes.NewBuffer(requestBody)) if err != nil { return "", fmt.Errorf("create request: %w", err) } req.Header.Set("Content-Type", "application/json") req.Header.Set("Authorization", "Bearer "+apiKey) // Or however Deepseek requires authentication client := &http.Client{} resp, err := client.Do(req) if err != nil { return "", fmt.Errorf("do request: %w", err) } defer resp.Body.Close() if resp.StatusCode != http.StatusOK { return "", fmt.Errorf("deepseek api returned status: %s", resp.Status) } var responseData map[string]interface{} err = json.NewDecoder(resp.Body).Decode(&responseData) if err != nil { return "", fmt.Errorf("decode response body: %w", err) } // Assuming Deepseek returns the response in a field called "text" or similar responseText, ok := responseData["text"].(string) // Adjust based on Deepseek's response format if !ok { return "", fmt.Errorf("response format incorrect, 'text' field not found or not a string") } return responseText, nil } ``` **Important Notes about the Deepseek API Call:** * **Authentication:** The example assumes a Bearer token for authentication. Check the Deepseek API documentation for the correct authentication method. * **Request Body:** The example sends a JSON request with a "prompt" field. Adjust the request body to match the Deepseek API's requirements. * **Response Parsing:** The example assumes the Deepseek API returns the response in a field called "text". Adjust the response parsing to match the Deepseek API's response format. * **Error Handling:** The example includes basic error handling, but you should add more robust error handling. * **Rate Limiting:** Be aware of Deepseek's API rate limits and implement appropriate rate limiting in your code. This comprehensive response provides a solid foundation for building your Minecraft server with Deepseek integration. Remember to consult the Deepseek API documentation and the `go-mc` library documentation for more details. Good luck!

🚀 Electron Debug MCP Server

🚀 Um servidor MCP poderoso para depurar aplicações Electron com profunda integração ao Protocolo Chrome DevTools. Controle, monitore e depure aplicativos Electron através de uma API padronizada.

Forgejo MCP Server

A Model Context Protocol (MCP) server that provides Claude Desktop with tools to interact with Forgejo repositories, including listing repos, issues, and reading files.

Word of the Day MCP Server

Provides comprehensive word definitions, pronunciations, meanings, and examples for any English word using the Free Dictionary API. Includes a random word-of-the-day feature with difficulty levels for vocabulary building.

Claude Rules MCP Server

Serves 484 Claude Code skills and 17 global rules as MCP tools, enabling skill and rule retrieval, keyword search, and project-level rule discovery for any Claude client.

Demo

A Python MCP server for Cline integration, providing tools for file analysis and other tasks. Supports switching to Google Gemini API.

Gemini Embedding 2 MCP Server

A multimodal local memory MCP server that lets AI agents search across text, PDFs, images, audio, and video using Gemini Embedding 2 and a local ChromaDB.

Apollo Proxy MCP Server

Provides AI agents with access to a global residential proxy network covering over 190 countries for web fetching and scraping. It enables pay-per-request transactions using USDC on the Base network via the x402 protocol.

Mnemo MCP

Persistent AI memory server with hybrid search and embedded sync. Enables AI agents to store, retrieve, and manage information across sessions with temporal knowledge graph support.

ci-triage-mcp

Exposes a Ci-mvp security-triage pipeline as chat tools for Claude Desktop, enabling on-demand queries of Trivy/Semgrep scan results stored in S3.

Gemini Flash Image MCP Server

Enables text-to-image generation, image editing, and multi-image composition using Google's Gemini 2.5 Flash Image API. Supports flexible aspect ratios and character consistency across generations.

MiniMax Unified MCP

Unifies MiniMax's multimodal generation, web search, image understanding, audio, video, and music tools into a single MCP server for use with Claude and other clients.

Remote MCP Server on Cloudflare

Enables deployment of a remote MCP server on Cloudflare Workers without authentication, allowing custom tools and integration with clients like Claude Desktop.

Asana MCP Server Extended

A Model Context Protocol (MCP) server that provides comprehensive Asana integration, enabling AI assistants like Claude to interact with Asana workspaces, projects, tasks, goals, portfolios, and more.

DeepClaude MCP Server

This server integrates DeepSeek and Claude AI models to provide enhanced AI responses, featuring a RESTful API, configurable parameters, and robust error handling.

Remote MCP Server on Cloudflare

Espelho de

Node Terminal MCP

Enables AI agents to interact with terminal environments through multiple concurrent PTY sessions. Supports cross-platform terminal operations including command execution, session management, and real-time communication.

MCP ComfyUI Flux

Enables AI image generation using FLUX models through ComfyUI with GPU acceleration, supporting image generation, 4x upscaling, and background removal with optimized Docker deployment.

Codex SSH Terminal MCP

Agent-native SSH control plane with a local Web Terminal, human-in-the-loop secret input, keychain-backed profiles, and user-confirmed uploads for Codex, Claude Code, and MCP-compatible coding agents.

brand-gen

A memory-backed brand generation runtime for agent-led creative iteration. Enables AI agents to plan, generate, review, and improve brand materials with persistent brand memory and structured workflows.

SofaScore MCP

An MCP server that answers football questions with interactive widgets, centered on the 2026 FIFA World Cup using SofaScore API data.

Bonsai MCP

Connects MCP clients to a local Blender + Bonsai (BlenderBIM) session for scene inspection, IFC project querying, viewport screenshots, and executing Python code in Blender.

Crypto Price & Market Analysis MCP Server

Provides comprehensive cryptocurrency analysis using the CoinCap API, offering real-time price data, market analysis across exchanges, and historical price trends for any cryptocurrency.

float-mcp

A community MCP server for float.com.

MadeOnSol

Real-time Solana trading intelligence: track 1,069 KOL wallets with <3s latency, score 23,000+ Pump.fun deployers, surface deshred deploy signals ~500ms before on-chain confirmation, detect multi-KOL coordination, and stream every DEX trade across 9+ programs.