Discover Awesome MCP Servers

MeSH MCP

Connects Claude to the U.S. National Library of Medicine MeSH APIs to search and retrieve medical authority data, descriptors, and qualifiers. It enables library and metadata staff to perform subject analysis and confirm terminology within an AI-assisted cataloging workflow.

linkrescue-mcp

MCP server for broken link detection, monitoring, and AI-powered fix suggestions. Scans URLs or sitemaps, estimates SEO and revenue impact, and returns actionable remediation steps. Built with FastMCP 3.x.

Twitter/X MCP Server

Enables AI agents to interact with Twitter/X through Playwright browser automation without requiring an official API key. It provides tools for posting content, searching tweets, reading feeds, and managing social interactions like follows and likes.

Atlassian Confluence MCP Server

Cermin dari

Search Service

Server Pencarian MCP memungkinkan integrasi tanpa hambatan antara kemampuan pencarian jaringan dan lokal dalam alat seperti Claude Desktop dan Cursor, menggunakan Brave Search API untuk konkurensi tinggi dan permintaan asinkron.

Figma MCP PRO

Professional Model Context Protocol server that enables AI-optimized Figma design analysis and comprehensive design-to-code conversion through a structured 5-step workflow.

DNDzgz MCP Server

An MCP server that provides real-time information about the Zaragoza tram system, including arrival estimations and station details through the DNDzgz API.

TCMB MCP

Provides access to Turkish Central Bank (TCMB) exchange rates with current and historical data since 1996, currency conversion, rate history statistics, and multi-currency comparisons with smart caching.

Klarna Payments MCP Server

An MCP server that enables interaction with Klarna's Payments API, allowing applications to implement Klarna payment options through natural language commands.

example-mcp-server-streamable-http

example-mcp-server-streamable-http

gloria-mcp

MCP server for Gloria AI curated crypto news. Provides curated, real-time cryptocurrency news digests, recaps, and search.

Tavily Web Search MCP Server

Enables web search capabilities through the Tavily API via the Model Context Protocol. Allows users to perform web searches and retrieve information from the internet through natural language queries.

lol-client-mcp Public

Sebuah server MCP (Model-Controller-Processor) untuk mengakses data klien League of Legends. Server ini menyediakan kumpulan alat yang berkomunikasi dengan League of Legends Live Client Data API untuk mengambil data dalam game.

Xueqiu MCP

Layanan MCP yang didasarkan pada API Xueqiu (pasar saham Tiongkok) yang memungkinkan pengguna untuk menanyakan data saham secara langsung melalui Claude atau asisten AI lainnya.

Cloud Pilot MCP

Provides AI agents with natural language control over AWS, Azure, GCP, and Alibaba Cloud infrastructure through dynamic API discovery and execution. Supports 51,900+ cloud operations and includes OpenTofu integration for complete infrastructure lifecycle management.

Claude Data Buddy

Enables conversational analysis of CSV and Parquet files through natural language, providing statistics, summaries, data type information, and comprehensive multi-step data analysis.

Mnemo Cortex

Persistent semantic memory for AI agents — hybrid SQLite + FTS5 with DAG-based summaries, context compaction, and 7 MCP tools. Open source, self-hosted, zero API cost.

MCP Store Greeting Server

Provides personalized store greetings combined with real-time weather information based on store location. Includes an admin web interface for managing stores with address autocomplete and map-based location selection.

filesystem-mcp

Server MCP berbasis TypeScript yang mengimplementasikan sistem catatan sederhana, memungkinkan pengguna untuk membuat, mengakses, dan menghasilkan ringkasan catatan teks melalui URI dan alat.

Electron MCP Server

A Model Context Protocol server that provides comprehensive Electron application automation, debugging, and observability capabilities through Chrome DevTools Protocol integration.

Elysia MCP Starter

A template for building Model Context Protocol servers using Elysia and Bun runtime, enabling LLM clients like Claude Desktop and Cody to access custom tools, prompts, and data resources.

Cloudflare Playwright MCP

Enables AI assistants to control a browser through Playwright on Cloudflare Workers, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.

Minecraft Survival MCP Server

Enables LLM agents to play and survive in Minecraft by abstracting low-level tasks like pathfinding, building, and crafting into high-level transactional commands. It utilizes a "Helix" architecture to handle execution and coordinate math autonomously, allowing models to focus on strategy and high-level intent.

MCP SQL Server

An MCP server for Microsoft SQL Server integration that enables users to query, monitor, and analyze databases directly through Claude. It supports schema exploration, performance analysis, and optional write operations via natural language commands.

JSer.info MCP Server

A Model Context Protocol server that provides search and retrieval capabilities for JSer.info's JavaScript resource database, enabling access to items, posts, product information, and timeline data through various specialized tools.

Dental Clinic Loan Verification MCP Server

Enables automated dental clinic loan verification by combining rule-based ID validation with LLM-powered document analysis and fraud detection. It supports provider-agnostic vision and reasoning tools to assess document consistency, verify credentials like PAN and GST, and generate comprehensive risk narratives.

MCP

Okay, here's a breakdown of how you might configure an MCP (presumably a "Management Control Panel" or similar) server to view company information and stock prices using the Claude API. This is a conceptual outline, as the specific implementation will depend heavily on your MCP's architecture, programming language, and existing data sources. **I. Understanding the Components** * **MCP Server:** This is the core of your system. It's the application that users interact with to view information. It likely has a database, a user interface (web-based or desktop), and backend logic. * **Claude API:** This is the interface to Anthropic's Claude model. You'll use it to query for company information and stock prices. You'll need an API key from Anthropic. * **Data Sources (Optional):** You might already have some company information stored in your MCP's database. You might also use a separate stock price API (e.g., Alpha Vantage, IEX Cloud, Finnhub) as a more reliable and structured source for stock data. Claude can *supplement* this data, but it's generally not a replacement for a dedicated stock API. * **Programming Language:** The language your MCP server is written in (e.g., Python, Java, Node.js, PHP) will determine the libraries and methods you use to interact with the Claude API. **II. High-Level Steps** 1. **Obtain an Anthropic API Key:** * Sign up for an account at Anthropic's website. * Obtain your API key. Keep this key secure! 2. **Choose a Programming Language and Libraries:** * Select the appropriate programming language for your MCP server. * Find a library or SDK that simplifies interacting with the Claude API in that language. If there isn't a dedicated library, you can use standard HTTP request libraries (e.g., `requests` in Python, `axios` in Node.js). 3. **Implement the API Integration:** * **Create a Function to Query Claude:** Write a function that takes a company name or stock ticker as input and sends a request to the Claude API. * **Craft the Prompt:** This is crucial. Design a prompt that tells Claude exactly what you want. For example: ``` "Provide a summary of [company_name], including its industry, key products/services, and recent news. Also, provide the current stock price and any recent price changes." ``` Replace `[company_name]` with the actual company name. Experiment with different prompts to get the best results. Be specific about the format you want the data in. * **Handle the API Response:** Parse the JSON response from Claude. Extract the relevant information (company summary, stock price, etc.). Handle potential errors (e.g., API key invalid, rate limits exceeded, Claude can't find the information). 4. **Integrate with Your MCP Server:** * **Add a User Interface Element:** Create a search box or form in your MCP's user interface where users can enter a company name or stock ticker. * **Connect the UI to the API Function:** When the user submits the form, call the function you created in step 3 to query the Claude API. * **Display the Results:** Format and display the information returned by Claude in a user-friendly way within your MCP. 5. **(Optional) Integrate with a Stock Price API:** * Sign up for an account with a stock price API provider (e.g., Alpha Vantage, IEX Cloud, Finnhub). * Obtain your API key. * Write a function to query the stock price API for the current stock price and recent price changes. * Use the stock price API data as the primary source for stock prices. You can still use Claude to *supplement* this data with news or analysis. 6. **Error Handling and Rate Limiting:** * Implement robust error handling to catch API errors, network issues, and other potential problems. * Be mindful of Claude's API rate limits. Implement caching or other strategies to avoid exceeding the limits. 7. **Security:** * **Never expose your API key in client-side code (e.g., JavaScript).** Store it securely on your server. * Sanitize user input to prevent prompt injection attacks. Be careful about directly passing user input into the Claude prompt. **III. Example (Conceptual - Python with `requests`)** ```python import requests import json ANTHROPIC_API_KEY = "YOUR_ANTHROPIC_API_KEY" # Replace with your actual API key def get_company_info_from_claude(company_name): """ Queries the Claude API for company information and stock price. """ prompt = f"Provide a summary of {company_name}, including its industry, key products/services, and recent news. Also, provide the current stock price and any recent price changes." headers = { "Content-Type": "application/json", "x-api-key": ANTHROPIC_API_KEY, "anthropic-version": "2023-06-01" # Or the latest version } data = { "model": "claude-v1.3", # Or the model you want to use "prompt": f"\n\nHuman: {prompt}\n\nAssistant:", "max_tokens_to_sample": 500 # Adjust as needed } try: response = requests.post("https://api.anthropic.com/v1/complete", headers=headers, data=json.dumps(data)) response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx) json_response = response.json() return json_response["completion"] # The text generated by Claude except requests.exceptions.RequestException as e: print(f"Error calling Claude API: {e}") return None except KeyError: print("Error parsing Claude API response.") return None # Example usage: company_name = "Apple Inc." company_info = get_company_info_from_claude(company_name) if company_info: print(company_info) else: print("Could not retrieve company information.") ``` **IV. Indonesian Translation of Key Concepts** * **MCP Server:** Server MCP (Panel Kontrol Manajemen) * **Claude API:** API Claude * **API Key:** Kunci API * **Prompt:** Perintah (instruksi ke model) * **Stock Price API:** API Harga Saham * **Rate Limiting:** Pembatasan Tingkat (jumlah permintaan per waktu) * **Error Handling:** Penanganan Kesalahan * **User Interface:** Antarmuka Pengguna * **Database:** Basis Data * **Security:** Keamanan * **Prompt Injection:** Injeksi Perintah (serangan keamanan) **V. Important Considerations** * **Claude's Limitations:** Claude is a language model, not a financial expert. The information it provides about stock prices and company performance should be considered *informational* and not financial advice. Always verify information from Claude with reliable sources. * **Data Accuracy:** Claude's knowledge is based on its training data, which may not be completely up-to-date. Stock prices change constantly, so relying solely on Claude for stock prices is risky. * **Prompt Engineering:** The quality of the information you get from Claude depends heavily on the prompt you provide. Experiment with different prompts to find what works best. * **Cost:** Using the Claude API incurs costs based on the number of tokens processed. Be mindful of your usage and budget. * **Alternatives:** Consider using a dedicated financial data provider for more accurate and reliable stock price information. You can still use Claude to summarize news articles or provide context, but use a dedicated API for the core financial data. This detailed outline should give you a good starting point for configuring your MCP server to use the Claude API. Remember to adapt the code and instructions to your specific environment and requirements. Good luck!

FastAPI MCP Server

Wraps FastAPI REST endpoints as MCP tools, enabling natural language interaction with user management, task management, and mathematical calculations through Gemini CLI.

Smithsonian Open Access MCP Server

Provides AI assistants with access to search, explore, and analyze over 3 million collection objects from the Smithsonian Institution's museums. Enables finding objects currently on exhibit, retrieving detailed metadata, high-resolution images, and 3D models from America's national museums.