发现优秀的 MCP 服务器

WooCommerce Enterprise MCP Suite

Provides 115+ MCP tools for comprehensive WooCommerce store management including multi-store operations, bulk processing, inventory sync, order management, and customer analytics. Features enterprise-level safety controls with dry-run mode, automatic backups, and rollback capabilities.

MCP Server

Facilitates multi-client processing for high-performance operations within the DigitalFate framework, enabling advanced automation through task orchestration and agent integration.

MCP AI Research Assistant

An offline MCP server that enables research tasks such as summarizing text, extracting key points, and saving/retrieving notes via a CLI client and stdio transport.

Great Question MCP Server

Enables AI assistants to conduct user research workflows directly from Great Question, including creating studies, recruiting participants, and querying insights.

mcp0

安全 MCP（模型上下文协议）服务器配置器/检查器，将配置的上下文暴露为 MCP 服务器。一次配置，可与任何 MCP 客户端重复使用。

ausecon-mcp-server

MCP server for structured Australian macroeconomic and financial data from the Australian Bureau of Statistics (ABS), the Reserve Bank of Australia (RBA), and the Australian Prudential Regulation Authority (APRA).

excalidash-mcp

MCP server for live collaborative drawing on ExcaliDash, enabling diagram creation and editing with instant browser updates via Socket.IO.

Local Services MCP Server

A Multi-Agent Conversation Protocol Server that provides access to Google's Local Services API, enabling interaction with local service businesses information through natural language commands.

Typesense MCP Server

A server that enables vector and keyword search capabilities in Typesense databases through the Model Context Protocol, providing tools for collection management, document operations, and search functionality.

🚀 MCP File System API

Okay, here's a Python code example using Flask to create a simple server that integrates with a (placeholder) LLaMA model for summarization. This example focuses on the structure and integration points. **Important considerations and placeholders are marked with comments.** ```python from flask import Flask, request, jsonify import torch # Import PyTorch #import llama # Placeholder: Replace with your actual LLaMA model import #from transformers import AutoTokenizer, AutoModelForSeq2SeqLM # Alternative for Hugging Face models app = Flask(__name__) # --- Model Loading and Setup --- # This section is CRUCIAL and needs to be adapted to your specific LLaMA model. # Option 1: If you have a custom LLaMA implementation # model = llama.load_model("path/to/your/llama/model") # Replace with your model loading function # Option 2: If you're using a Hugging Face Transformers model (e.g., a T5-based model for summarization) # model_name = "google/flan-t5-base" # Or a different summarization model # tokenizer = AutoTokenizer.from_pretrained(model_name) # model = AutoModelForSeq2SeqLM.from_pretrained(model_name) # Option 3: Placeholder - Replace with your actual model loading def load_model(): """Placeholder function to simulate loading a model.""" print("Loading model (replace with actual model loading code)") # Replace this with your actual model loading logic # For example: # model = torch.load("path/to/your/model.pth") # model.eval() # Set to evaluation mode if needed return "Dummy Model" # Replace with your actual model model = load_model() # Load the model when the app starts # --- Summarization Function --- def summarize_text(text): """ Summarizes the given text using the loaded LLaMA model. Args: text: The input text to summarize. Returns: The summarized text. """ print(f"Summarizing text: {text[:50]}...") # Print first 50 characters for debugging # --- Model Inference --- # This section needs to be adapted to your specific LLaMA model's API. # Option 1: Custom LLaMA model # summary = model.summarize(text) # Replace with your model's summarization function # Option 2: Hugging Face Transformers model # inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True) # summary_ids = model.generate(inputs.input_ids, max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True) # summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True) # Option 3: Placeholder - Replace with your actual model inference code summary = f"Placeholder Summary for: {text[:20]}..." # Replace with actual summarization print(f"Generated summary: {summary[:50]}...") # Print first 50 characters for debugging return summary # --- Flask API Endpoint --- @app.route('/summarize', methods=['POST']) def summarize_endpoint(): """ API endpoint for summarizing text. Expects a JSON payload with a 'text' field. """ try: data = request.get_json() text = data.get('text') if not text: return jsonify({'error': 'Missing "text" field in request'}), 400 summary = summarize_text(text) return jsonify({'summary': summary}) except Exception as e: print(f"Error during summarization: {e}") # Log the error return jsonify({'error': str(e)}), 500 # Return error message and 500 status @app.route('/health', methods=['GET']) def health_check(): """Simple health check endpoint.""" return jsonify({'status': 'ok'}) if __name__ == '__main__': app.run(debug=True, host='0.0.0.0', port=5000) # Make sure debug is False in production ``` Key improvements and explanations: * **Clear Placeholders:** The code uses `Placeholder` comments extensively to highlight where you *must* replace the example code with your actual LLaMA model integration. This is the most important part. * **Error Handling:** Includes `try...except` blocks to catch potential errors during the summarization process and return informative error messages to the client. This is crucial for debugging and production stability. * **Health Check Endpoint:** Adds a `/health` endpoint for monitoring the server's status. This is essential for deployment and monitoring. * **Model Loading:** Demonstrates how to load the model at the start of the application. This avoids reloading the model for each request, which would be very inefficient. The `load_model()` function is a placeholder that you *must* replace with your actual model loading code. * **Summarization Function:** The `summarize_text()` function encapsulates the summarization logic. This makes the code more modular and easier to test. Again, the model inference part is a placeholder. * **Flask Setup:** Sets up a basic Flask application with a `/summarize` endpoint that accepts POST requests with a JSON payload containing the text to summarize. * **JSON Handling:** Uses `request.get_json()` to properly parse the JSON payload from the request. * **Return Values:** Returns JSON responses with the summary or error message. * **Logging:** Includes `print` statements for debugging. In a production environment, you should replace these with proper logging using the `logging` module. * **Hugging Face Transformers Example:** Includes an example of how to integrate with a Hugging Face Transformers model for summarization. This is a common way to use pre-trained models. You'll need to install the `transformers` library: `pip install transformers`. * **`host='0.0.0.0'`:** This makes the server accessible from outside the local machine. Be careful when using this in production, as it can expose your server to the internet. * **`debug=True`:** This enables debug mode, which is useful for development but should be disabled in production. * **Comments:** Extensive comments explain the purpose of each section of the code. **How to Use:** 1. **Install Flask:** `pip install Flask` 2. **Install PyTorch:** `pip install torch` (if you are using PyTorch) 3. **Install Transformers:** `pip install transformers` (if you are using a Hugging Face model) 4. **Replace Placeholders:** **This is the most important step.** Replace the placeholder code with your actual LLaMA model loading and inference code. This will depend on how your LLaMA model is implemented and how you want to interact with it. 5. **Run the Application:** `python your_script_name.py` 6. **Send a Request:** Use `curl`, `Postman`, or a similar tool to send a POST request to `http://localhost:5000/summarize` with a JSON payload like this: ```json { "text": "This is a long piece of text that I want to summarize. It contains many sentences and paragraphs. The goal is to reduce the text to its most important points." } ``` **Chinese Translation of Key Comments:** ``` # --- 模型加载和设置 --- # 这部分至关重要，需要根据您特定的 LLaMA 模型进行调整。 # --- 模型推理 --- # 这部分需要根据您特定的 LLaMA 模型的 API 进行调整。 # 替换占位符：这是最重要的步骤。将占位符代码替换为您实际的 LLaMA 模型加载和推理代码。这将取决于您的 LLaMA 模型是如何实现的，以及您希望如何与它交互。 ``` **Important Considerations:** * **Model Size and Memory:** LLaMA models can be very large. Make sure you have enough memory to load and run the model. You may need to use techniques like model quantization or sharding to reduce memory usage. * **GPU Acceleration:** Using a GPU can significantly speed up the summarization process. Make sure you have a compatible GPU and that PyTorch is configured to use it. * **Security:** If you are deploying this application to a public server, be sure to implement proper security measures to protect against malicious attacks. * **Rate Limiting:** Implement rate limiting to prevent abuse of the API. * **Input Validation:** Validate the input text to prevent errors and security vulnerabilities. * **Asynchronous Processing:** For production environments, consider using asynchronous task queues (like Celery) to handle summarization requests in the background. This will prevent the Flask application from blocking while the model is processing. * **Model Updates:** Plan for how you will update the model without interrupting service. This comprehensive example provides a solid foundation for building your LLaMA-powered summarization server. Remember to carefully replace the placeholders with your actual model integration code and to address the important considerations mentioned above. Good luck!

mcp-python-sandbox

A lightweight MCP server that enables any MCP client to execute Python code safely in a sandboxed environment, with automatic matplotlib inline image return and temporary file isolation.

nodejs-mcp-mongodb

MCP server that exposes MongoDB business data via tools for summary statistics, new users, and pending payments.

PlanckBot

An adaptive tiny-model layer that sits between an LLM and its MCP tools, compressing verbose tool outputs to reduce token usage by up to two orders of magnitude.

Twelve Data MCP Server

Provides integration with Twelve Data API to access financial market data including historical time series, real-time quotes, and instrument metadata for stocks, forex pairs, and cryptocurrencies.

nutrition-mcp

Local-first nutrition tracker MCP server for Hermes, enabling food, alias, recipe, and meal log management with SQLite persistence.

connecta

One MCP to rule them all. A single MCP endpoint that aggregates many downstream connectors — remote MCP servers and plain HTTP APIs — and presents agents a fixed set of nine meta-tools.

teammate-mcp

Enables Claude Code and OpenAI Codex to ask each other questions through iTerm panes, with no daemon or per-project configuration.

Gmail MCP Server

Provides comprehensive Gmail integration with 25+ tools for intelligent email management, including AI-powered categorization, advanced search and filtering, automated archiving and cleanup, analytics, and secure OAuth2 authentication.

Hong Kong Transportation MCP Server

An MCP server providing access to Hong Kong transportation data, including passenger traffic statistics at control points and real-time bus arrival information for KMB and Long Win Bus services.

Adobe Learning Manager MCP Server

Enables LLM clients to interact with Adobe Learning Manager, including user management, learning object browsing, enrollment management, badge checking, and async job execution via the ALM Prime API.

digeguigui

Global reptile & exotic pet knowledge base. 633 species, AI identification, genetics calculator, 12-dimension care, health diagnosis, pricing, provenance. Free 9 tools, 10 req/min.

resend-email-mcp

The most complete Resend MCP server — full coverage of the Resend API (emails, domains, contacts, broadcasts, templates, segments, topics, webhooks, logs) plus a unique debug/diagnostics layer no other Resend MCP offers: deliverability analysis, DNS troubleshooting, email lifecycle inspection, bounce explanation, and account auditing. Works with Claude Code, Cursor, Claude Desktop, and any other

INSEE MCP Server

Enables searching companies in the SIRENE database using SIREN, SIRET, or company name via the INSEE API.

Obsidian MCP Server

Enables AI assistants to manage and search Obsidian notes, folders, metadata, and links directly.

MCP Skills Manager

A server that serves reusable markdown skills (instructions, playbooks, references) to agents, with a web UI for editing and organizing skills, profiles, and both HTTP and stdio transports.

Blackbaud FE NXT MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Blackbaud FE NXT (beta): https://www.cdata.com/download/download.aspx?sku=OZZK-V&type=beta

Obsidian Tools MCP Server

Enables comprehensive management of Obsidian vaults with full CRUD operations, advanced search, link/tag extraction, backlinks discovery, frontmatter editing, and template-based note creation through natural language.

AgentVeil Protocol

Trust, identity, and reputation infrastructure for AI agents. Register agents with W3C DID (Ed25519), check EigenTrust reputation scores, submit peer attestations, search agents by capability, and verify IPFS-anchored audit trails. 11 tools.

Creative Ideation MCP Server

Utilizes the Google Gemini API to generate context-specific categories and diverse options for creative brainstorming. It features a random sampling function to help users bypass predictable AI patterns and discover unexpected, innovative ideas.