Discover Awesome MCP Servers

Electron MCP Server

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

MCP OAuth Server

A production-ready MCP server with OAuth 2.1 and PKCE for secure third-party API access, featuring GitHub user info retrieval and LLM-powered code analysis.

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.

Slack MCP Server

Enables complete Slack integration through natural language in Cursor IDE, supporting message sending, channel management, direct messaging, user lookup, reactions, and message search using the Slack API.

contrastapi

Security intelligence API for AI models. CVE lookup with EPSS/KEV, domain recon (DNS, WHOIS, SSL, subdomains, WAF), and code security checks (secrets, injection, headers). 16 tools, no API key required.

Postgres MCP Server

Enables comprehensive PostgreSQL database management through natural language including queries, schema operations, user management, and administrative tasks. Features enterprise-grade connection pooling, transaction support, and full database administration capabilities.

WorkOS MCP Server

MCP server for WorkOS User Management API. Enables Claude to manage users, organizations, memberships, invitations, and sessions in WorkOS.

mcp-tool-filter

A generic MCP proxy that filters which tools are exposed from a remote MCP server, reducing context window token usage by only loading the tools you actually need.

Benin OpenData MCP

MCP server to navigate and consume public data from Benin's OpenData portal.

RedTeam MCP

Autonomous penetration testing powered by a local LLM, automating tool chaining for recon, vulnerability scanning, exploit research, and reporting.

Order Status Server

Laravel MCP server that provides a tool to look up order status by order ID from a MySQL database.

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.

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 (Management Console Program, assuming that's what you mean) 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 the MCP server software you're using and the capabilities it offers. **High-Level Overview** The core idea is to: 1. **Get an API Key for Claude:** You'll need an account with Anthropic (the creators of Claude) and obtain an API key. This key is essential for authenticating your requests to the Claude API. 2. **Develop a Script/Module:** Create a script (likely in Python, Node.js, or a similar language) that uses the Claude API to fetch company information and stock prices. This script will take company names or stock tickers as input. 3. **Integrate the Script with your MCP Server:** Configure your MCP server to execute this script when a user requests company information or stock prices. This might involve creating a custom command, a plugin, or using the server's scripting capabilities. 4. **Display the Results:** Format the data returned by the script and display it within the MCP server's interface. **Detailed Steps and Considerations** 1. **Obtain a Claude API Key:** * Go to the Anthropic website ([https://www.anthropic.com/](https://www.anthropic.com/)) and sign up for an account. * Follow their instructions to obtain an API key. Keep this key secret and secure. Do *not* hardcode it directly into your script. Use environment variables or a secure configuration file. 2. **Choose a Programming Language and Install the Claude SDK (if available):** * Python is a popular choice for interacting with APIs. * Check if Anthropic provides an official SDK for your chosen language. If so, install it using `pip install anthropic` (for Python) or the equivalent for your language. If there's no official SDK, you'll use the `requests` library (in Python) or a similar HTTP client to make API calls. 3. **Write the Script to Fetch Company Information and Stock Prices:** ```python import os import requests import json # Replace with your actual API key (ideally from an environment variable) CLAUDE_API_KEY = os.environ.get("CLAUDE_API_KEY") if not CLAUDE_API_KEY: print("Error: CLAUDE_API_KEY environment variable not set.") exit(1) def get_company_info(company_name): """Fetches company information using the Claude API.""" prompt = f"Tell me about {company_name}. Include a brief description of what they do, their industry, and their headquarters location." try: response = requests.post( "https://api.anthropic.com/v1/messages", # Replace with the correct Claude API endpoint headers={ "Content-Type": "application/json", "x-api-key": CLAUDE_API_KEY, "Anthropic-Version": "2023-06-01" # Or the latest version }, json={ "model": "claude-v1.3", # Or the model you want to use "max_tokens_to_sample": 500, "messages": [{"role": "user", "content": prompt}] } ) response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx) data = response.json() return data["content"][0]["text"] # Extract the response text except requests.exceptions.RequestException as e: return f"Error fetching company info: {e}" except (KeyError, IndexError) as e: return f"Error parsing Claude response: {e}" def get_stock_price(ticker_symbol): """Fetches stock price using a different API (e.g., Alpha Vantage, IEX Cloud).""" # You'll need to sign up for an API key with a stock data provider. # This is just an example using Alpha Vantage (replace with your chosen provider). ALPHA_VANTAGE_API_KEY = os.environ.get("ALPHA_VANTAGE_API_KEY") if not ALPHA_VANTAGE_API_KEY: return "Error: ALPHA_VANTAGE_API_KEY environment variable not set." url = f"https://www.alphavantage.co/query?function=GLOBAL_QUOTE&symbol={ticker_symbol}&apikey={ALPHA_VANTAGE_API_KEY}" try: response = requests.get(url) response.raise_for_status() data = response.json() if "Global Quote" in data and data["Global Quote"]: price = data["Global Quote"]["05. price"] return f"The current price of {ticker_symbol} is ${price}" else: return f"Could not retrieve stock price for {ticker_symbol}." except requests.exceptions.RequestException as e: return f"Error fetching stock price: {e}" except (KeyError, IndexError) as e: return f"Error parsing Alpha Vantage response: {e}" if __name__ == "__main__": company = input("Enter a company name: ") company_info = get_company_info(company) print(f"Company Information:\n{company_info}\n") ticker = input("Enter a stock ticker symbol: ") stock_price = get_stock_price(ticker) print(f"Stock Price:\n{stock_price}") ``` * **Important Notes:** * **Error Handling:** The code includes basic error handling (using `try...except`). Improve this to handle different API errors gracefully. * **API Rate Limits:** Be aware of the API rate limits for both Claude and your stock data provider. Implement appropriate delays or caching to avoid exceeding these limits. * **API Endpoint:** Double-check the correct Claude API endpoint in the Anthropic documentation. The example uses `https://api.anthropic.com/v1/messages`, but this might change. * **Model Selection:** Choose the appropriate Claude model (e.g., `claude-v1.3`, `claude-v2`) based on your needs and the Anthropic documentation. * **Prompt Engineering:** The `prompt` is crucial. Experiment with different prompts to get the best results from Claude. Be specific about the information you want. * **Stock Data API:** The example uses Alpha Vantage. You can use other stock data providers like IEX Cloud, Finnhub, or Polygon.io. You'll need to sign up for an API key with your chosen provider. * **Security:** Never hardcode your API keys directly into the script. Use environment variables or a secure configuration file. 4. **Integrate the Script with your MCP Server:** * This is the most MCP-server-specific part. Consult your MCP server's documentation for how to: * **Execute External Scripts:** Most MCP servers have a way to run external scripts or programs. * **Create Custom Commands:** You might be able to create a custom command that takes a company name or ticker as input and then executes your script. * **Develop Plugins/Modules:** Some MCP servers allow you to develop plugins or modules to extend their functionality. This would be the most robust approach. * **Pass Arguments:** Make sure you can pass the company name or ticker symbol from the MCP server to your script as an argument. You can use `sys.argv` in Python to access command-line arguments. * **Example (Conceptual):** Let's say your MCP server has a command called `get_info`. You might configure it so that when a user types: ``` get_info company=AcmeCorp ``` The MCP server executes your Python script with `AcmeCorp` as an argument. Your script would then retrieve the company information and return it to the MCP server. 5. **Display the Results in the MCP Server:** * Your script needs to return the company information and stock price in a format that the MCP server can understand and display. This might be plain text, JSON, or some other format. * The MCP server will then need to format and display the data in its user interface. Consult your MCP server's documentation for how to customize the display of command output or plugin data. **Example MCP Server Integration (Conceptual - Python & Hypothetical MCP Server)** ```python # This is a simplified example. The actual implementation will depend on your MCP server. import sys import json from your_script import get_company_info, get_stock_price # Import your functions def main(): if len(sys.argv) < 2: print("Usage: get_info company=<company_name> or get_info ticker=<ticker_symbol>") return args = {} for arg in sys.argv[1:]: try: key, value = arg.split("=", 1) args[key] = value except ValueError: print(f"Invalid argument: {arg}") return if "company" in args: company_name = args["company"] company_info = get_company_info(company_name) print(json.dumps({"type": "company_info", "data": company_info})) # Return JSON elif "ticker" in args: ticker_symbol = args["ticker"] stock_price = get_stock_price(ticker_symbol) print(json.dumps({"type": "stock_price", "data": stock_price})) # Return JSON else: print("Invalid arguments. Use company=<company_name> or ticker=<ticker_symbol>") if __name__ == "__main__": main() ``` In this example: * The script takes arguments from the command line (e.g., `company=AcmeCorp`). * It calls your `get_company_info` or `get_stock_price` functions. * It returns the results as a JSON string. This makes it easier for the MCP server to parse the data. * The MCP server would need to be configured to execute this script and parse the JSON output. **Important Considerations:** * **Security:** Protect your API keys. Use environment variables or secure configuration files. Sanitize user input to prevent injection attacks. * **Error Handling:** Implement robust error handling to catch API errors, network errors, and other potential problems. * **Rate Limiting:** Be mindful of API rate limits and implement appropriate delays or caching. * **Data Accuracy:** The accuracy of the information depends on the quality of the data sources (Claude and your stock data provider). Verify the information before making any decisions based on it. * **Cost:** Be aware of the costs associated with using the Claude API and your stock data provider's API. Monitor your usage to avoid unexpected charges. * **Terms of Service:** Carefully review the terms of service for both Claude and your stock data provider to ensure that your use case is permitted. **In Summary** This is a complex integration that requires a good understanding of your MCP server, the Claude API, and a programming language like Python. Start with a simple script to fetch company information, then gradually integrate it with your MCP server and add more features. Remember to consult the documentation for your MCP server and the Claude API for the most accurate and up-to-date information. Good luck!

uk-gazette

Enables querying official UK public records from The Gazette, including insolvencies, winding-up petitions, and deceased estates.

rubberduck-mcp

Bridges AI assistants with Rubberduck VBA to enable code analysis, module management, and Git operations on VBA projects.

sap-bdc-mcp

Enables AI agents to safely discover and validate SAP Business Data Cloud contracts (ORD, CSN, share plans) with enterprise guardrails like redaction and read-only defaults.

power_defect_analysis_mcp

Enables querying and analysis of thermal power plant defects and work orders through fixed, parameterized SQL tools. Provides 8 core tools plus extensions for equipment search, defect/work order details, summaries, and failure analysis, with strict data boundaries and security.

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.

Agent Nudge

A local-first MCP server for AI coding agents that shares structured execution state, routes context deltas, and provides preflight nudges to prevent conflicts and stale decisions.

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.

legacy-mongodb-mcp

Provides read-only access to legacy MongoDB instances (<4.0) via the Model Context Protocol, enabling AI models to query databases, collections, and run aggregations safely.

GSC MCP Worker

MCP server for Google Search Console, providing tools for site properties, search analytics, URL inspection, sitemaps, and audit reports.

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.

jimeng-web-mcp

Provides direct access to Jimeng AI's web interface for generating images and videos, supporting features like multi-image generation, video creation with frame control, and batch operations using free daily credits.

gh-board-mcp

Manages GitHub Projects v2 as a personal kanban board, allowing you to create, move, and prioritize draft items without linking to real issues.

SEFAZ ES DEC: Caixa Postal

Enables querying the SEFAZ ES DEC postal mailbox from official sources via a single MCP tool.

ActionsPulse

Real-time GitHub Actions observability through VS Code with GitHub Copilot, providing DevOps metrics and interactive dashboards.

mod-dev-mcp

A development tooling MCP server for tModLoader mod projects, enabling building, formatting, and log tailing operations directly from an MCP client.