发现优秀的 MCP 服务器

MCP JSON Database Server

A JSON-based database MCP server with JWT authentication that enables user management, project tracking, department analysis, meeting management, and equipment tracking. Integrates with Claude Desktop to provide secure CRUD operations and analytics through natural language commands.

Trino MCP Server

镜子 (jìng zi)

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.

MCP Weather Server

Enables AI agents to access real-time and historical weather data through multiple weather APIs including OpenMeteo, Tomorrow.io, and OpenWeatherMap. Provides comprehensive meteorological information including current conditions, forecasts, historical data, and weather alerts.

Quarkus Model Context Protocol (MCP) Server

这个扩展程序使开发者能够轻松地实现 MCP 服务器的各项功能。

Reality Calendar MCP Server

Enables interaction with tool data stored in Google Drive Excel files through cached SQLite database. Provides access to tool information and descriptions with automatic background synchronization and OpenWebUI compatibility via OpenAI proxy.

Local iMessage RAG MCP Server

来自 Anthropic MCP 黑客马拉松 (纽约) 的 iMessage RAG MCP 服务器

Parallels RAS MCP Server (Python)

Here are a few possible translations, depending on the nuance you want to convey: **Option 1 (Most Direct):** * **Simplified Chinese:** 使用 FastAPI 的 Parallels RAS 的 MCP 服务器 * **Traditional Chinese:** 使用 FastAPI 的 Parallels RAS 的 MCP 伺服器 This is a straightforward translation. It's clear and accurate. **Option 2 (Slightly More Natural, Emphasizing "Built with"):** * **Simplified Chinese:** 基于 FastAPI 的 Parallels RAS MCP 服务器 * **Traditional Chinese:** 基於 FastAPI 的 Parallels RAS MCP 伺服器 This option uses "基于" (jī yú) which translates to "based on" or "built upon." It implies that the MCP server is constructed using FastAPI. **Option 3 (More Descriptive, Emphasizing "For"):** * **Simplified Chinese:** 用于 Parallels RAS 的基于 FastAPI 的 MCP 服务器 * **Traditional Chinese:** 用於 Parallels RAS 的基於 FastAPI 的 MCP 伺服器 This option uses "用于" (yòng yú) which translates to "for" or "intended for." It emphasizes that the MCP server is designed to be used with Parallels RAS. **Which one should you use?** * If you just need a simple, direct translation, **Option 1** is fine. * If you want to emphasize that the server is *built using* FastAPI, **Option 2** is better. * If you want to emphasize that the server is *designed for* Parallels RAS, **Option 3** is best. In most cases, **Option 1 or 2** will be the most appropriate. Choose the one that best fits the context.

MCP with Langchain Sample Setup

Okay, here's a sample setup for an MCP (presumably referring to a **Multi-Client Processing** or **Message Communication Protocol**) server and client, designed to be compatible with LangChain. This example focuses on a simple request-response pattern, suitable for offloading LangChain tasks to a separate process or machine. **Important Considerations:** * **Serialization:** LangChain objects can be complex. You'll need a robust serialization/deserialization method (e.g., `pickle`, `json`, `cloudpickle`) to send data between the server and client. `cloudpickle` is often preferred for its ability to handle more complex Python objects, including closures and functions. * **Error Handling:** Implement comprehensive error handling on both the server and client to gracefully manage exceptions and network issues. * **Security:** If you're transmitting data over a network, consider security measures like encryption (e.g., TLS/SSL) to protect sensitive information. * **Asynchronous Operations:** For better performance, especially with LangChain tasks that might be I/O bound, consider using asynchronous programming (e.g., `asyncio`). This example shows a basic synchronous version for clarity. * **Message Format:** Define a clear message format (e.g., JSON with specific keys) for requests and responses. * **LangChain Compatibility:** The key is to serialize the *input* to a LangChain component (like a Chain or LLM) on the client, send it to the server, deserialize it, run the LangChain component on the server, serialize the *output*, and send it back to the client. **Python Code (using `socket` module for simplicity):** **1. Server (server.py):** ```python import socket import pickle # Or json, cloudpickle import langchain import os # Example LangChain setup (replace with your actual chain) from langchain.llms import OpenAI from langchain.chains import LLMChain from langchain.prompts import PromptTemplate os.environ["OPENAI_API_KEY"] = "YOUR_API_KEY" # Replace with your actual API key llm = OpenAI(temperature=0.7) prompt = PromptTemplate( input_variables=["product"], template="What is a good name for a company that makes {product}?", ) chain = LLMChain(llm=llm, prompt=prompt) HOST = '127.0.0.1' # Standard loopback interface address (localhost) PORT = 65432 # Port to listen on (non-privileged ports are > 1023) def process_langchain_request(data): """ Processes a LangChain request. This is the core logic on the server. """ try: # Deserialize the input (assuming it's a dictionary) input_data = pickle.loads(data) # Or json.loads(data) if using JSON # **Crucially, ensure the input_data matches what your LangChain component expects.** # For example, if your chain expects a dictionary with a "text" key: # input_text = input_data["text"] # Run the LangChain component result = chain.run(input_data["product"]) # Replace with your actual LangChain call # Serialize the result serialized_result = pickle.dumps(result) # Or json.dumps(result) return serialized_result except Exception as e: print(f"Error processing request: {e}") return pickle.dumps({"error": str(e)}) # Serialize the error message with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.bind((HOST, PORT)) s.listen() print(f"Server listening on {HOST}:{PORT}") conn, addr = s.accept() with conn: print(f"Connected by {addr}") while True: data = conn.recv(4096) # Adjust buffer size as needed if not data: break response = process_langchain_request(data) conn.sendall(response) ``` **2. Client (client.py):** ```python import socket import pickle # Or json, cloudpickle HOST = '127.0.0.1' # The server's hostname or IP address PORT = 65432 # The port used by the server def send_langchain_request(input_data): """ Sends a LangChain request to the server and returns the response. """ try: with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) # Serialize the input data serialized_data = pickle.dumps(input_data) # Or json.dumps(input_data) s.sendall(serialized_data) received = s.recv(4096) # Adjust buffer size as needed # Deserialize the response deserialized_response = pickle.loads(received) # Or json.loads(received) return deserialized_response except Exception as e: print(f"Error sending request: {e}") return {"error": str(e)} if __name__ == "__main__": # Example usage input_data = {"product": "eco-friendly cleaning products"} # Replace with your actual input response = send_langchain_request(input_data) if "error" in response: print(f"Error from server: {response['error']}") else: print(f"Server response: {response}") ``` **How to Run:** 1. **Install LangChain:** `pip install langchain openai` 2. **Set your OpenAI API Key:** Replace `"YOUR_API_KEY"` in `server.py` with your actual OpenAI API key. 3. **Run the server:** `python server.py` 4. **Run the client:** `python client.py` **Explanation:** * **Server (`server.py`):** * Creates a socket and listens for incoming connections. * When a client connects, it receives data, deserializes it (using `pickle`), processes it using a LangChain component (in this case, a simple `LLMChain`), serializes the result, and sends it back to the client. * Includes basic error handling. * **Client (`client.py`):** * Creates a socket and connects to the server. * Serializes the input data (using `pickle`), sends it to the server, receives the response, deserializes it, and prints the result. * Includes basic error handling. * **Serialization:** `pickle` (or `json`, `cloudpickle`) is used to convert Python objects into a byte stream that can be sent over the network. The same method must be used for both serialization and deserialization. * **LangChain Integration:** The `process_langchain_request` function on the server is where the LangChain logic resides. It receives the serialized input, deserializes it, runs the LangChain component, and serializes the output. **Key Improvements and Considerations for Production:** * **Asynchronous Communication (using `asyncio`):** Use `asyncio` for non-blocking I/O, allowing the server to handle multiple clients concurrently. This significantly improves performance. * **Message Queues (e.g., RabbitMQ, Redis):** Instead of direct socket connections, use a message queue for more robust and scalable communication. This decouples the client and server and allows for asynchronous processing. * **gRPC:** Consider using gRPC for efficient and type-safe communication between the client and server. gRPC uses Protocol Buffers for serialization, which is generally faster and more compact than `pickle` or `json`. * **Authentication and Authorization:** Implement authentication and authorization to secure the server and prevent unauthorized access. * **Logging:** Use a logging library (e.g., `logging`) to record events and errors for debugging and monitoring. * **Configuration:** Use a configuration file (e.g., YAML, JSON) to store settings like the server address, port, and API keys. * **Monitoring:** Monitor the server's performance and resource usage to identify bottlenecks and potential issues. * **Data Validation:** Validate the input data on both the client and server to prevent errors and security vulnerabilities. * **Retry Logic:** Implement retry logic on the client to handle transient network errors. * **Heartbeat Mechanism:** Implement a heartbeat mechanism to detect and handle server failures. * **Cloudpickle:** For complex LangChain objects, especially those involving custom functions or classes, `cloudpickle` is often necessary to ensure proper serialization and deserialization. Install it with `pip install cloudpickle`. **Example using `cloudpickle`:** ```python # Server (server.py) import cloudpickle def process_langchain_request(data): try: input_data = cloudpickle.loads(data) result = chain.run(input_data["product"]) serialized_result = cloudpickle.dumps(result) return serialized_result except Exception as e: print(f"Error processing request: {e}") return cloudpickle.dumps({"error": str(e)}) # Client (client.py) import cloudpickle def send_langchain_request(input_data): try: with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: s.connect((HOST, PORT)) serialized_data = cloudpickle.dumps(input_data) s.sendall(serialized_data) received = s.recv(4096) deserialized_response = cloudpickle.loads(received) return deserialized_response except Exception as e: print(f"Error sending request: {e}") return {"error": str(e)} ``` This more complete example provides a solid foundation for building a distributed LangChain application. Remember to adapt the code to your specific needs and consider the production-level improvements mentioned above. **Chinese Translation of Key Concepts:** * **MCP (Multi-Client Processing/Message Communication Protocol):** 多客户端处理/消息通信协议 (Duō kèhùduān chǔlǐ/Xiāoxī tōngxìn xiéyì) * **Serialization:** 序列化 (Xùlièhuà) * **Deserialization:** 反序列化 (Fǎn xùlièhuà) * **LangChain:** LangChain (No direct translation, use the English name) * **Socket:** 套接字 (Tàojiēzì) * **Asynchronous:** 异步 (Yìbù) * **Message Queue:** 消息队列 (Xiāoxī duìliè) * **gRPC:** gRPC (No direct translation, use the English name) * **Protocol Buffers:** 协议缓冲区 (Xiéyì huǎnchōngqū) * **Authentication:** 身份验证 (Shēnfèn yànzhèng) * **Authorization:** 授权 (Shòuquán) * **Logging:** 日志记录 (Rìzhì jìlù) * **Cloudpickle:** Cloudpickle (No direct translation, use the English name) This should give you a good starting point. Let me know if you have any more specific questions.

tasksync-mcp

MCP server to give new instructions to agent while its working. It uses the get_feedback tool to collect your input from the feedback.md file in the workspace, which is sent back to the agent when you save.

FastAPI MCP-Style Server

A minimal FastAPI implementation that mimics Model Context Protocol functionality with JSON-RPC 2.0 support. Provides basic tools like echo and text transformation through both REST and RPC endpoints for testing MCP-style interactions.

Enterprise Template Generator

Enables generation of enterprise-grade software templates with built-in GDPR/Swedish compliance validation, workflow automation for platform migrations, and comprehensive template management through domain-driven design principles.

gorse

Data On Tap Inc. 是一家在加拿大运营网络 302 100 的完整 MVNO（移动虚拟网络运营商）。这是 DOT 的代码仓库。它包括高级安全和身份验证、各种连接工具、智能功能（包括智能网络预留）、eSIM/iSIM、引导无线连接、D2C 卫星、构建框架和概念，以及 OpenAPI 3.1 和 MCP 服务器。

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.

缔零法则Lawgenesis

缔零法则MCP是基于LLM和RAG技术搭建的实现完全替代人力的全自动化风险识别的内容安全审查平台，致力于通过代理AI技术减少人力成本，高效高精度为用户提供分钟级接入的内容风控解决方案，破解安全威胁，提供从风险感知到主动拦截策略执行的全链路闭环与一体化解决方案。This MCP tool is an AI-powered content security review platform built on LLM and RAG technologies, designed to achieve fully automated risk identification that completel

Accounting MCP Server

Enables personal financial management through AI assistants by providing tools to add transactions, check balances, list transaction history, and generate monthly summaries. Supports natural language interaction for tracking income and expenses with categorization.

Zerodha Trading Bot - MCP Server

A Model Context Protocol server that integrates with Zerodha APIs for automated trading, providing tools for authentication, market data retrieval, order placement, and portfolio management.

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.

Mcp Namecheap Registrar

连接到 Namecheap API，用于检查域名可用性和价格，并注册域名。

Cursor Rust Tools

一个 MCP 服务器，用于让 Cursor 中的 LLM 访问 Rust Analyzer、Crate 文档和 Cargo 命令。

Build

Okay, I can help you understand how to use the TypeScript SDK to create different MCP (Mesh Configuration Protocol) servers. However, I need a little more context to give you the *most* helpful answer. Specifically, tell me: 1. **Which MCP SDK are you using?** There are several possibilities, including: * **Istio's MCP SDK (likely part of the `envoyproxy/go-control-plane` project, but you'd be using the TypeScript bindings).** This is the most common use case if you're working with Istio or Envoy. * **A custom MCP implementation.** If you're building your own MCP server from scratch, you'll need to define your own data structures and server logic. * **Another MCP SDK.** There might be other, less common, MCP SDKs available. 2. **What kind of MCP server do you want to create?** What specific resources will it serve? For example: * **Route Configuration (RDS) server:** Serves route configurations to Envoy proxies. * **Cluster Configuration (CDS) server:** Serves cluster definitions to Envoy proxies. * **Listener Configuration (LDS) server:** Serves listener configurations to Envoy proxies. * **Endpoint Discovery Service (EDS) server:** Serves endpoint information to Envoy proxies. * **A custom resource server:** Serves your own custom resource types. 3. **What is your desired level of detail?** Do you want: * **A high-level overview of the process?** * **Example code snippets?** * **A complete, runnable example?** (This would be more complex and require more information from you.) **General Steps (Assuming Istio/Envoy MCP):** Here's a general outline of the steps involved in creating an MCP server using a TypeScript SDK (assuming it's based on the Envoy/Istio MCP protocol): 1. **Install the Necessary Packages:** You'll need to install the appropriate TypeScript packages. This will likely involve: * The core gRPC library for TypeScript (`@grpc/grpc-js` or similar). * The generated TypeScript code from the Protocol Buffers (`.proto`) definitions for the MCP resources you want to serve (e.g., `envoy.config.route.v3`, `envoy.config.cluster.v3`, etc.). You'll typically use `protoc` (the Protocol Buffer compiler) and a TypeScript plugin to generate these files. * Potentially, a library that provides helper functions for working with MCP. ```bash npm install @grpc/grpc-js google-protobuf # And potentially other packages depending on your setup ``` 2. **Generate TypeScript Code from Protocol Buffers:** You'll need to obtain the `.proto` files that define the MCP resources (e.g., from the `envoyproxy/go-control-plane` repository or your own custom definitions). Then, use `protoc` to generate TypeScript code from these files. This will create the TypeScript classes that represent the resource types. Example `protoc` command (you'll need to adjust this based on your `.proto` file locations and plugin configuration): ```bash protoc --plugin=protoc-gen-ts=./node_modules/.bin/protoc-gen-ts --ts_out=. your_mcp_resource.proto ``` 3. **Implement the gRPC Service:** Create a TypeScript class that implements the gRPC service defined in the `.proto` files. This class will have methods that correspond to the MCP endpoints (e.g., `StreamRoutes`, `StreamClusters`, etc.). These methods will receive requests from Envoy proxies and return the appropriate resource configurations. 4. **Handle the MCP Stream:** The core of an MCP server is handling the bidirectional gRPC stream. Your service implementation will need to: * Receive `DiscoveryRequest` messages from the client (Envoy proxy). * Process the request, determining which resources the client is requesting. * Fetch the appropriate resource configurations from your data store (e.g., a database, a configuration file, or in-memory data). * Construct `DiscoveryResponse` messages containing the resource configurations. * Send the `DiscoveryResponse` messages back to the client. * Handle errors and stream termination gracefully. 5. **Manage Resource Versions (Important for Updates):** MCP uses versioning to ensure that clients receive consistent updates. You'll need to track the versions of your resources and include them in the `DiscoveryResponse` messages. When a client sends a `DiscoveryRequest`, it will include the version of the resources it currently has. Your server should only send updates if the client's version is out of date. 6. **Implement a Data Store (Configuration Source):** You'll need a way to store and manage the resource configurations that your MCP server serves. This could be a simple configuration file, a database, or a more complex configuration management system. 7. **Start the gRPC Server:** Use the gRPC library to start a gRPC server and register your service implementation with it. The server will listen for incoming connections from Envoy proxies. 8. **Configure Envoy to Use Your MCP Server:** Configure your Envoy proxies to connect to your MCP server. This will typically involve specifying the server's address and port in the Envoy configuration. **Example (Conceptual - Requires Adaptation):** ```typescript // Assuming you've generated TypeScript code from your .proto files // import { RouteDiscoveryServiceService, RouteDiscoveryServiceHandlers } from './route_discovery_grpc_pb'; // import { DiscoveryRequest, DiscoveryResponse } from './discovery_pb'; import * as grpc from '@grpc/grpc-js'; // Replace with your actual generated code interface DiscoveryRequest { versionInfo: string; node: any; // Replace with your Node type resourceNames: string[]; typeUrl: string; responseNonce: string; errorDetail: any; // Replace with your Status type } interface DiscoveryResponse { versionInfo: string; resources: any[]; // Replace with your Resource type typeUrl: string; nonce: string; controlPlane: any; // Replace with your ControlPlane type } interface RouteDiscoveryServiceHandlers { streamRoutes: grpc.ServerDuplexStream<DiscoveryRequest, DiscoveryResponse>; } class RouteDiscoveryServiceImpl implements RouteDiscoveryServiceHandlers { streamRoutes(stream: grpc.ServerDuplexStream<DiscoveryRequest, DiscoveryResponse>): void { stream.on('data', (request: DiscoveryRequest) => { console.log('Received request:', request); // Fetch route configurations based on the request const routes = this.fetchRoutes(request); // Construct the DiscoveryResponse const response: DiscoveryResponse = { versionInfo: 'v1', // Replace with your versioning logic resources: routes, typeUrl: 'envoy.config.route.v3.RouteConfiguration', // Replace with your resource type URL nonce: 'some-nonce', // Generate a unique nonce controlPlane: null, // Replace if you have control plane info }; stream.write(response); }); stream.on('end', () => { console.log('Stream ended'); stream.end(); }); stream.on('error', (err) => { console.error('Stream error:', err); stream.end(); }); } private fetchRoutes(request: DiscoveryRequest): any[] { // Implement your logic to fetch route configurations // based on the request parameters (e.g., resourceNames, versionInfo) // This is where you would access your data store. console.log("fetching routes"); return [ { name: 'route1', domains: ['example.com'] }, { name: 'route2', domains: ['test.com'] }, ]; // Replace with actual route configurations } } function main() { const server = new grpc.Server(); // server.addService(RouteDiscoveryServiceService, new RouteDiscoveryServiceImpl()); server.addService({streamRoutes: {path: "/envoy.service.discovery.v3.RouteDiscoveryService/StreamRoutes", requestStream: true, responseStream: true, requestSerialize: (arg: any) => Buffer.from(JSON.stringify(arg)), requestDeserialize: (arg: Buffer) => JSON.parse(arg.toString()), responseSerialize: (arg: any) => Buffer.from(JSON.stringify(arg)), responseDeserialize: (arg: Buffer) => JSON.parse(arg.toString())}}, new RouteDiscoveryServiceImpl()); server.bindAsync('0.0.0.0:50051', grpc.ServerCredentials.createInsecure(), (err, port) => { if (err) { console.error('Failed to bind:', err); return; } console.log(`Server listening on port ${port}`); server.start(); }); } main(); ``` **Important Considerations:** * **Error Handling:** Implement robust error handling to gracefully handle unexpected situations. * **Logging:** Add logging to help you debug and monitor your MCP server. * **Security:** Secure your gRPC server using TLS/SSL. * **Scalability:** Consider the scalability of your MCP server, especially if you're serving a large number of Envoy proxies. * **Testing:** Thoroughly test your MCP server to ensure that it's working correctly. **Next Steps:** 1. **Tell me which MCP SDK you're using.** 2. **Tell me what kind of MCP server you want to create.** 3. **Tell me your desired level of detail.** Once I have this information, I can provide you with more specific and helpful guidance.

Test Generator MCP Server

Enables automatic generation of test scenarios from user stories uploaded to Claude desktop. Leverages MCP integration to streamline the test case creation process for development workflows.

ActionKit MCP Starter

Okay, here's a translation of "Starter code for a MCP server powered by ActionKit" into Chinese, along with a few options depending on the nuance you want to convey: **Option 1 (Most Literal):** * **基于 ActionKit 的 MCP 服务器的起始代码** * (Jīyú ActionKit de MCP fúwùqì de qǐshǐ dàimǎ) This is a direct translation. It's clear and understandable. **Option 2 (Slightly More Natural):** * **使用 ActionKit 构建的 MCP 服务器的初始代码** * (Shǐyòng ActionKit gòujiàn de MCP fúwùqì de chūshǐ dàimǎ) This emphasizes that ActionKit is used to *build* the server. "构建 (gòujiàn)" means "to build" or "to construct." **Option 3 (Focus on Getting Started):** * **用于 ActionKit 驱动的 MCP 服务器的入门代码** * (Yòng yú ActionKit qūdòng de MCP fúwùqì de rùmén dàimǎ) This emphasizes that the code is for *getting started* with an ActionKit-powered server. "入门 (rùmén)" means "entry-level" or "getting started." "驱动 (qūdòng)" means "driven by" or "powered by." **Option 4 (Concise and Common):** * **ActionKit MCP 服务器的初始代码** * (ActionKit MCP fúwùqì de chūshǐ dàimǎ) This is a more concise version, assuming the context makes it clear that the code is *for* the server. It's common to omit "基于" or "使用" in Chinese when it's implied. **Which option is best depends on the specific context:** * If you want to be very precise and literal, use Option 1. * If you want to emphasize the building aspect, use Option 2. * If you want to emphasize that it's for beginners, use Option 3. * If you want a concise and common phrasing, use Option 4. **Key Vocabulary:** * **起始代码 (qǐshǐ dàimǎ) / 初始代码 (chūshǐ dàimǎ):** Starter code, initial code * **MCP 服务器 (MCP fúwùqì):** MCP server * **基于 (jīyú):** Based on * **使用 (shǐyòng):** To use * **构建 (gòujiàn):** To build, to construct * **驱动 (qūdòng):** Driven by, powered by * **入门 (rùmén):** Entry-level, getting started I hope this helps! Let me know if you have any other questions.

MCP MySQL Server

Enables interaction with MySQL databases (including AWS RDS and cloud instances) through natural language. Supports database connections, query execution, schema inspection, and comprehensive database management operations.

Mcp Servers Collection

已验证的 MCP 服务器和集成集合