Discover Awesome MCP Servers

Salesforce MCP Server

Enables authenticated interaction with Salesforce through OAuth Bearer token forwarding. Allows users to make API calls to Salesforce instances while maintaining secure session-based authentication throughout the MCP lifecycle.

MCP Server Starter

A starter template for building MCP servers with SQLite database integration. Provides a foundation with SQL query tools, database seeding capabilities, and a development client for testing.

ServiceNow CMDB MCP Server

Enables interaction with ServiceNow CMDB tables through a Model Context Protocol server, allowing users to query any CMDB table with filtering, field selection, and pagination capabilities.

Bocha Search MCP

Một công cụ tìm kiếm tập trung vào AI, cho phép các ứng dụng AI tiếp cận kiến thức chất lượng cao từ hàng tỷ trang web và các nguồn nội dung hệ sinh thái trên nhiều lĩnh vực khác nhau, bao gồm thời tiết, tin tức, bách khoa toàn thư, thông tin y tế, vé tàu và hình ảnh.

Build

Okay, I can help you understand how to create different MCP (Meta-Control Protocol) servers using the TypeScript SDK. However, I need a little more information to give you the *most* helpful and specific answer. Please tell me: 1. **Which MCP SDK are you using?** There are several possibilities. Knowing the specific SDK is crucial. Some common ones (or related concepts) include: * **Epic Games MCP SDK:** This is likely what you're referring to if you're working with Fortnite or other Epic Games services. It's often used for managing player data, entitlements, and other game-related information. * **Other MCP implementations:** "MCP" can also refer to more generic meta-control protocols in other contexts (e.g., in distributed systems, cloud management). If you're *not* using the Epic Games SDK, please specify which one you are using. * **Custom MCP:** Are you building your own MCP server and client? 2. **What do you mean by "different"?** What aspects of the MCP server do you want to customize or differentiate? For example: * **Different environments (dev, staging, production):** This is a common use case. You'll likely want different configurations for each environment. * **Different game features:** Perhaps you want different MCP servers to handle different aspects of your game (e.g., one for matchmaking, one for inventory). * **Different regions:** You might need separate MCP servers for different geographical regions to reduce latency. * **Different data models:** Are you using different data structures or schemas for different purposes? * **Different authentication/authorization:** Do you need different ways to authenticate users or authorize access to resources? 3. **What have you tried so far?** Do you have any existing code or configuration that you can share? This will help me understand your current setup and provide more targeted guidance. **General Concepts (Assuming Epic Games MCP SDK):** Here's a breakdown of the general concepts involved in creating different MCP servers, assuming you're using the Epic Games MCP SDK (or something similar): * **Configuration:** The most common way to create "different" MCP servers is through configuration. You'll typically have configuration files (e.g., JSON, YAML, or TypeScript files) that specify: * **Server endpoints:** The URLs or IP addresses where the MCP server listens for requests. * **Database connections:** The connection strings for the databases that the MCP server uses to store data. * **Authentication settings:** The credentials and methods used to authenticate clients. * **Entitlement settings:** The rules for granting and managing entitlements. * **Feature flags:** Settings that enable or disable specific features of the MCP server. * **Logging levels:** The level of detail to include in the server's logs. * **Environment Variables:** Environment variables are often used to override configuration settings, especially in production environments. This allows you to change the behavior of the MCP server without modifying the code or configuration files. * **Code Separation (If Necessary):** In some cases, you might need to create separate codebases for different MCP servers. This is more likely if you have significantly different data models or business logic. However, it's generally better to use configuration and feature flags to differentiate servers whenever possible. * **Deployment:** You'll need to deploy each MCP server to a separate environment (e.g., a different virtual machine, container, or cloud instance). This ensures that the servers are isolated from each other. **Example (Conceptual - Needs SDK Details):** Let's say you want to create different MCP servers for development and production environments. Here's a conceptual example of how you might do it: 1. **Create Configuration Files:** * `config/development.json`: ```json { "serverEndpoint": "http://localhost:8080", "databaseUrl": "mongodb://localhost:27017/mcp_dev", "authenticationEnabled": false, "loggingLevel": "debug" } ``` * `config/production.json`: ```json { "serverEndpoint": "https://mcp.example.com", "databaseUrl": "mongodb://prod-db-server:27017/mcp_prod", "authenticationEnabled": true, "authenticationProvider": "EpicGames", "loggingLevel": "info" } ``` 2. **Load Configuration in TypeScript:** ```typescript import * as fs from 'fs'; import * as path from 'path'; interface Config { serverEndpoint: string; databaseUrl: string; authenticationEnabled: boolean; authenticationProvider?: string; loggingLevel: string; } function loadConfig(env: string): Config { const configPath = path.join(__dirname, 'config', `${env}.json`); const configData = fs.readFileSync(configPath, 'utf8'); return JSON.parse(configData); } const environment = process.env.NODE_ENV || 'development'; // Default to development const config = loadConfig(environment); // Now you can use the 'config' object to configure your MCP server. console.log(`Running in ${environment} environment`); console.log(`Server endpoint: ${config.serverEndpoint}`); // Example: Initialize your MCP server with the configuration // (This part depends on the specific MCP SDK) // const mcpServer = new McpServer(config); // mcpServer.start(); ``` 3. **Set Environment Variable:** * When running in production, set the `NODE_ENV` environment variable to `production`: ```bash export NODE_ENV=production node your-mcp-server.js ``` **Important Considerations:** * **Security:** Pay close attention to security when configuring MCP servers, especially in production environments. Use strong authentication methods, encrypt sensitive data, and regularly audit your security settings. * **Scalability:** Design your MCP servers to be scalable so that they can handle increasing traffic and data volumes. Consider using load balancing, caching, and database sharding. * **Monitoring:** Implement monitoring to track the performance and health of your MCP servers. Set up alerts to notify you of any issues. * **Logging:** Use comprehensive logging to help you troubleshoot problems and understand how your MCP servers are being used. **Next Steps:** Please provide the information I requested at the beginning of this response (SDK, "different" meaning, and what you've tried). With that information, I can give you much more specific and helpful guidance.

Iris MCP Server

A multi-backend gateway that enables access to various services like Google Drive and Notion through a single MCP connector. It currently provides comprehensive Google Drive integration for reading, writing, and managing files and folders.

Prompt Bookmarks

Enables users to organize, search, and manage a shared library of prompts across AI tools via the Model Context Protocol. It supports hierarchical folder organization, tagging, and template variable substitution for dynamic prompt generation.

MCP Think

A Model Context Protocol server that provides AI assistants like Claude with a dedicated space for structured thinking during complex problem-solving tasks.

Android Puppeteer

Enables AI agents to interact with Android devices through visual UI element detection and automated interactions. Provides comprehensive Android automation capabilities including touch gestures, text input, screenshots, and video recording via uiautomator2.

Model Context Protocol (MCP) Server

A Python implementation of the MCP server that enables AI models to connect with external tools and data sources through a standardized protocol, supporting tool invocation and resource access via JSON-RPC.

Elasticsearch MCP Server

Enables Claude Desktop to connect directly to Elasticsearch clusters for intelligent log analysis through natural language queries. Users can ask questions about their logs in plain English and get actionable insights without writing complex Elasticsearch queries.

mcp-server-db2i

Enables AI assistants to query and inspect IBM DB2 for i databases using read-only SQL commands and schema inspection tools. It provides secure access to table metadata, views, and indexes via the JT400 JDBC driver.

ChatRPG

A lightweight ChatGPT app that converts your LLM into a Dungeon Master!

FastMCP Demo Server

A production-ready MCP server that provides hackathon resources and reusable starter prompts. Built with FastMCP framework and includes comprehensive deployment options for development and production environments.

Parallels RAS MCP Server (Python)

Máy chủ MCP cho Parallels RAS sử dụng FastAPI

Google Search MCP Server

A Model Context Protocol server that provides web and image search capabilities through Google's Custom Search API, allowing AI assistants like Claude to access current information from the internet.

Vercel Functions MCP Server Template

A template for deploying MCP servers on Vercel with serverless functions. Includes example tools for rolling dice and fetching weather data to demonstrate basic tool implementation and API integration patterns.

Mnehmos Synch

Provides persistent context synchronization and memory management for AI agents across sessions and projects, including file indexing, bug tracking, spatial navigation, and agent-to-agent handoff coordination.

mintlify-mcp

An MCP server that enables users to query any Mintlify-powered documentation site directly from Claude. It leverages Mintlify's AI Assistant API to provide RAG-based answers and code examples for various platforms like Agno, Resend, and Upstash.

DevOps Helper MCP

Provides tools and slash commands to onboard developers and manage DevOps workflows including Git operations, Docker containerization, GitHub Actions CI/CD, GitHub Container Registry, SonarCloud code analysis, and Azure container deployments.

Claude Code DingTalk MCP Server

Integrates Claude Code with DingTalk (钉钉) robot notifications, allowing users to send task completion alerts and various message formats to DingTalk groups from Claude Code.

market-data-mcp

Real-time financial market data MCP server. Stocks, crypto, technicals, sentiment, FDA calendar. No API keys required.

Devici MCP Server

Provides LLM tools to interact with the Devici API, enabling management of threat modeling resources including users, collections, threat models, components, threats, mitigations, and teams.

Tagging MCP

Enables parallel tagging and classification of CSV data using multiple LLM providers with structured output, confidence scores, and optional reasoning for batch classification tasks.

OmniFocus MCP Server

Tích hợp OmniFocus của Claude: Cho phép LLM tương tác với các tác vụ của bạn thông qua Giao thức Ngữ cảnh Mô hình. Thêm, sắp xếp và truy vấn cơ sở dữ liệu OmniFocus của bạn bằng các lệnh ngôn ngữ tự nhiên.

Files MCP Server

Enables AI agents to safely explore directories, read files, search content by pattern or filename, and edit files with checksum verification and dry-run preview within sandboxed filesystem access.

Copilot Studio Agent Direct Line MCP Server

Enables interaction with Microsoft Copilot Studio Agents directly from VS Code through the Direct Line 3.0 API. Supports starting conversations, sending messages, retrieving history, and managing conversation lifecycle with your custom agents.

semantic-edit-mcp

semantic-edit-mcp

Continuo Memory System

Enables persistent memory and semantic search for development workflows with hierarchical compression. Store and retrieve development knowledge across IDE sessions using natural language queries, circumventing context window limitations.