Discover Awesome MCP Servers

tokencost-dev

LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM. An MCP server that gives AI assistants accurate, up-to-date model pricing from the LiteLLM community registry. Look up pricing and capabilities for any LLM with fuzzy matching, estimate costs for token volumes, and compare models by provider, context window, or mode.

Concurrent Browser MCP

A concurrent browser MCP server that supports multiple parallel browser instances

MCP Browser Text Reader

Controls a real Chrome browser to navigate web pages and extract text content with flexible options including CSS selectors, multiple text extraction types, and intelligent waiting mechanisms for dynamic content.

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-hilton

An MCP server that enables AI agents to search Hilton hotels, manage reservations, and check Hilton Honors status through browser automation. It supports the full booking flow, points redemption, and digital key access via natural language commands.

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.

Plane MCP Server

A Model Context Protocol (MCP) server that enables LLMs to interact with Plane.so, allowing them to manage projects and issues through Plane's API. Using this server, LLMs like Claude can directly interact with your project management workflows while maintaining user control and security.

MCP

Okay, let's break down how you can configure an MCP (presumably, you mean a **Monitoring and Control Platform** or a similar system) to view company information and stock prices using Claude (likely referring to the **Anthropic Claude AI model**). This involves several steps and considerations. I'll outline a general approach, and you'll need to adapt it to your specific MCP and its capabilities. **High-Level Overview** The core idea is to: 1. **Gather Data:** Get company information and stock prices from reliable sources (APIs, databases, etc.). 2. **Send Data to Claude:** Format the data and send it to the Claude API with a clear prompt. 3. **Receive and Parse Claude's Response:** Claude will analyze the data and provide insights. You need to parse this response. 4. **Display in MCP:** Integrate the parsed information into your MCP's interface. **Detailed Steps** **1. Data Acquisition** * **Company Information:** * **APIs:** Use APIs like the Crunchbase API, Clearbit API, or similar services that provide company profiles, funding information, employee counts, industry, etc. These usually require an API key and have usage limits. * **Databases:** If your company has its own database of company information, you can directly query that. * **Web Scraping (Use with Caution):** As a last resort, you *could* scrape websites like LinkedIn or company websites. However, web scraping is fragile (websites change), and you need to respect robots.txt and terms of service. It's generally better to use APIs. * **Stock Prices:** * **Financial APIs:** Use APIs like Alpha Vantage, IEX Cloud, Finnhub, or Yahoo Finance API (though Yahoo Finance's API is less reliable than it used to be). These provide real-time or near real-time stock prices, historical data, and other financial metrics. Again, you'll need an API key. * **Data Providers:** Consider professional data providers like Refinitiv or Bloomberg if you need very high-quality, low-latency data, but these are significantly more expensive. **2. Data Preparation and Formatting** * **Data Cleaning:** Clean the data you retrieve. Handle missing values, inconsistencies, and errors. * **Data Aggregation:** Combine the company information and stock price data into a single data structure (e.g., a Python dictionary or a JSON object) for each company you want to analyze. * **Prompt Engineering:** This is crucial for getting useful results from Claude. Craft a clear and specific prompt that tells Claude what you want it to do. Here's an example: ```python prompt = f""" Analyze the following information about {company_name}: Company Description: {company_description} Industry: {company_industry} Employee Count: {company_employee_count} Current Stock Price: {stock_price} Previous Day's Closing Price: {previous_close} Provide a brief summary of the company, its current financial situation based on the stock price, and potential risks or opportunities. Focus on key insights that would be relevant to a business analyst. Keep the response concise (under 200 words). """ ``` * **Variables:** Replace the placeholders (e.g., `{company_name}`, `{stock_price}`) with the actual data you've collected. * **Instructions:** Clearly tell Claude what you want it to do (summarize, analyze, identify risks, etc.). * **Context:** Provide enough context for Claude to understand the data. * **Constraints:** Set limits on the response length to avoid overly verbose outputs. * **Role:** You can even specify a role for Claude to play, such as "Act as a financial analyst..." **3. Sending Data to Claude (Using the API)** * **Install the Anthropic Python Library:** ```bash pip install anthropic ``` * **API Key:** You'll need an API key from Anthropic. Get one from their website after signing up for an account. * **Code Example (Python):** ```python import anthropic import os # Replace with your actual API key ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY") # Best practice: store API key in an environment variable client = anthropic.Anthropic(api_key=ANTHROPIC_API_KEY) def get_claude_response(prompt): try: completion = client.completions.create( model="claude-v1.3", # Or a newer Claude model prompt=f"{anthropic.HUMAN_PROMPT} {prompt}{anthropic.AI_PROMPT}", max_tokens_to_sample=500, # Adjust as needed ) return completion.completion except Exception as e: print(f"Error calling Claude API: {e}") return None # Example usage: company_name = "Apple Inc." company_description = "Designs, develops, and sells consumer electronics, computer software, and online services." company_industry = "Technology" company_employee_count = 164000 stock_price = 175.00 previous_close = 173.50 prompt = f""" Analyze the following information about {company_name}: Company Description: {company_description} Industry: {company_industry} Employee Count: {company_employee_count} Current Stock Price: {stock_price} Previous Day's Closing Price: {previous_close} Provide a brief summary of the company, its current financial situation based on the stock price, and potential risks or opportunities. Focus on key insights that would be relevant to a business analyst. Keep the response concise (under 200 words). """ claude_response = get_claude_response(prompt) if claude_response: print(f"Claude's Analysis for {company_name}:\n{claude_response}") else: print("Failed to get a response from Claude.") ``` * **`anthropic.HUMAN_PROMPT` and `anthropic.AI_PROMPT`:** These are special tokens that help Claude understand the structure of the conversation. Always include them. * **`model`:** Specify the Claude model you want to use (e.g., "claude-v1.3", "claude-v2"). Check the Anthropic documentation for the latest models. * **`max_tokens_to_sample`:** Controls the maximum length of Claude's response. Adjust this based on your needs. * **Error Handling:** Include `try...except` blocks to handle potential errors when calling the API. **4. Parsing Claude's Response** * **Text Extraction:** The `completion.completion` attribute contains the text response from Claude. * **Structured Data (Optional):** If you want Claude to return structured data (e.g., JSON), you can modify your prompt to request it. However, Claude is not always perfect at generating valid JSON, so you might need to use regular expressions or other parsing techniques to extract the data reliably. For example: ```python prompt = f""" Analyze the following information about {company_name}: Company Description: {company_description} Industry: {company_industry} Employee Count: {company_employee_count} Current Stock Price: {stock_price} Previous Day's Closing Price: {previous_close} Provide a JSON object with the following keys: - summary: A brief summary of the company. - financial_outlook: A brief assessment of the company's financial situation. - risks: Potential risks. - opportunities: Potential opportunities. Example JSON: {{ "summary": "...", "financial_outlook": "...", "risks": "...", "opportunities": "..." }} """ ``` Then, you would try to parse the `claude_response` as JSON: ```python import json try: data = json.loads(claude_response) print(f"Summary: {data['summary']}") print(f"Financial Outlook: {data['financial_outlook']}") except json.JSONDecodeError: print("Could not parse Claude's response as JSON.") # Handle the error (e.g., use a regular expression to extract the data) ``` **5. Integration with Your MCP** * **MCP API/SDK:** Your MCP likely has an API or SDK that allows you to integrate external data sources. Consult your MCP's documentation for details. * **Data Visualization:** Use your MCP's charting and visualization tools to display the company information, stock prices, and Claude's analysis. * **Alerting:** Configure alerts based on stock price changes or specific insights from Claude (e.g., "Alert if Claude identifies a significant risk for Apple"). **Example Architecture** ``` [Data Sources (APIs, Databases)] --> [Data Aggregation & Formatting (Python Script)] --> [Claude API] --> [Response Parsing (Python Script)] --> [MCP API] --> [MCP Dashboard] ``` **Important Considerations** * **API Costs:** Be aware of the costs associated with using APIs like the Anthropic API and financial data APIs. Monitor your usage and set limits to avoid unexpected charges. * **Rate Limiting:** APIs often have rate limits (e.g., a maximum number of requests per minute). Implement error handling and retry mechanisms to deal with rate limiting. * **Data Accuracy:** The accuracy of Claude's analysis depends on the quality of the data you provide. Verify the data from your sources. * **Security:** Protect your API keys and other sensitive information. Store them securely (e.g., in environment variables) and avoid hardcoding them in your code. * **Prompt Engineering is Key:** Experiment with different prompts to get the best results from Claude. Iterate and refine your prompts based on the responses you receive. * **Claude's Limitations:** Claude is a powerful language model, but it's not perfect. It can sometimes make mistakes or provide inaccurate information. Always critically evaluate its output. * **Legal and Ethical Considerations:** Be mindful of data privacy regulations and ethical considerations when using company information and stock prices. Ensure you have the right to use the data and that you are not violating any laws or regulations. **Translation to Portuguese (of the key concepts):** * **Monitoring and Control Platform:** Plataforma de Monitoramento e Controle * **Anthropic Claude AI model:** Modelo de IA Claude da Anthropic * **API:** API (Interface de Programação de Aplicações) * **API Key:** Chave de API * **Prompt Engineering:** Engenharia de Prompt (ou Criação de Instruções) * **Data Cleaning:** Limpeza de Dados * **Data Aggregation:** Agregação de Dados * **Rate Limiting:** Limitação de Taxa * **Data Visualization:** Visualização de Dados * **Alerting:** Alertas **Example Portuguese Prompt:** ``` Analise as seguintes informações sobre a [Nome da Empresa]: Descrição da Empresa: [Descrição da Empresa] Indústria: [Indústria] Número de Funcionários: [Número de Funcionários] Preço Atual das Ações: [Preço Atual das Ações] Preço de Fechamento do Dia Anterior: [Preço de Fechamento do Dia Anterior] Forneça um breve resumo da empresa, sua situação financeira atual com base no preço das ações e potenciais riscos ou oportunidades. Concentre-se em insights importantes que seriam relevantes para um analista de negócios. Mantenha a resposta concisa (abaixo de 200 palavras). ``` **In summary, this is a complex integration that requires careful planning, coding, and testing. Start with a small, well-defined use case and gradually expand as you gain experience.** Remember to consult the documentation for your MCP and the Anthropic Claude API for the most up-to-date information. 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.

Magic Hour MCP Server

Enables AI-powered media manipulation including face swapping for videos and photos, lip syncing, and face detection via the Magic Hour AI platform. It provides tools for uploading files, managing video projects, and processing content from both local files and YouTube URLs.

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.

Atlassian Bitbucket MCP

Enables interaction with Bitbucket through the Model Context Protocol, allowing users to manage pull requests, add comments, review code, create tasks, and perform other repository operations using natural language.

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.

Cloud IoT API MCP Server

A Multi-Agent Conversation Protocol server that provides an interface to Google's Cloud IoT API, allowing agents to interact with and manage IoT devices and registries through natural language.

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.

SocialGuessSkills

A multi-agent framework that models complex social systems through a coordinated workflow of seven specialized agents covering areas like economics, governance, and risk. It enables users to generate structured, verifiable social system models from basic assumptions using the Model Context Protocol.

CC Fig MCP

Enables bidirectional control between Claude Code and Figma with real-time sync, allowing creation and manipulation of design elements, component management, and document inspection through natural language commands.

touch-grass

Claude Code plugin and MCP server that nudges you to take outdoor breaks based on local weather, sunset timing, and session streaks. Exposes check_grass_conditions, suggest_activity, log_touch_grass, and get_stats tools — fully local, no API keys, no cloud storage.

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.

Laravel AI MCP Server

Provides AI assistants with direct access to Laravel documentation, coding rules, and implementation templates stored locally. It enables searching documentation, retrieving design system guides, and accessing domain-specific code examples to streamline Laravel development.

Search Service

O Servidor Search MCP permite a integração perfeita de recursos de pesquisa de rede e local em ferramentas como Claude Desktop e Cursor, utilizando a API Brave Search para solicitações assíncronas e de alta simultaneidade.

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.

Medium MCP Server

Enables AI assistants to interact with Medium's platform for publishing, updating, and managing articles and drafts through OAuth 2.0 authentication with automatic retry logic and rate limit handling.

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.