Discover Awesome MCP Servers

viraill-mcp

Enables MCP clients to audit AI search visibility, generate intent-aligned social content, and assess Agentic Commerce Readiness with remediation files.

fortimanager-mcp

This MCP server provides tools to interact with FortiManager via JSON-RPC, but is deprecated and replaced by a more efficient Code Mode architecture.

automatised-pipeline

A Rust MCP server that indexes codebases into a property graph and provides tools for code intelligence, such as searching, context, impact analysis, and change detection.

TeslaMate MCP Server

Exposes TeslaMate HTTP APIs (health, logging, drive GPX) and a generic API request tool for interacting with a TeslaMate instance via MCP.

Scryfall MCP Server

Provides AI assistants with access to Magic: The Gathering card data via Scryfall API, enabling card search, image downloads, and database management.

Facebook Marketplace MCP

Enables searching Facebook Marketplace listings from Claude using your existing Facebook session without a browser.

Aws Sample Gen Ai Mcp Server

Okay, here's a sample code snippet demonstrating how to use Gen-AI (specifically, Bedrock) with an MCP (presumably, a message processing or communication platform) server. I'll provide a Python example, as it's commonly used for both Gen-AI and server-side scripting. I'll make some assumptions about your MCP server's API, but you'll need to adapt it to your specific setup. **Conceptual Overview** 1. **Receive Message:** The MCP server receives a message (e.g., from a user). 2. **Extract Text:** The relevant text from the message is extracted. 3. **Send to Bedrock:** The text is sent to Amazon Bedrock for processing (e.g., text generation, summarization, translation). 4. **Receive Response:** Bedrock returns a response. 5. **Format Response:** The response is formatted for sending back to the user. 6. **Send to MCP Server:** The formatted response is sent back to the MCP server to be delivered to the user. **Python Example (using Boto3 for Bedrock)** ```python import boto3 import json from flask import Flask, request, jsonify # Example using Flask for MCP server app = Flask(__name__) # Configure AWS Bedrock bedrock = boto3.client( service_name='bedrock-runtime', region_name='your-aws-region', # Replace with your AWS region (e.g., 'us-east-1') endpoint_url='your-bedrock-endpoint-url' # Replace with your Bedrock endpoint URL if needed ) model_id = 'anthropic.claude-v2' # Example model ID. Change as needed. # MCP Server Endpoint (Example using Flask) @app.route('/process_message', methods=['POST']) def process_message(): try: data = request.get_json() user_message = data.get('message') # Assuming the message is in a 'message' field if not user_message: return jsonify({'error': 'No message provided'}), 400 # Call Bedrock bedrock_response = invoke_bedrock(user_message) # Format the response (adapt to your MCP server's requirements) formatted_response = { 'response': bedrock_response, 'original_message': user_message } # Send the response back to the MCP server (in this example, we just return it) return jsonify(formatted_response), 200 except Exception as e: print(f"Error processing message: {e}") return jsonify({'error': str(e)}), 500 def invoke_bedrock(prompt): """Invokes the Bedrock model with the given prompt.""" body = json.dumps({ "prompt": prompt, "max_tokens_to_sample": 200, # Adjust as needed "temperature": 0.5, # Adjust as needed "top_p": 0.9 # Adjust as needed }) try: response = bedrock.invoke_model( modelId=model_id, contentType="application/json", accept="application/json", body=body ) response_body = json.loads(response['body'].read()) completion = response_body['completion'] return completion except Exception as e: print(f"Error invoking Bedrock: {e}") return f"Error: {e}" if __name__ == '__main__': app.run(debug=True, port=5000) # Adjust port as needed ``` **Explanation:** 1. **Imports:** Imports necessary libraries (boto3 for Bedrock, Flask for the MCP server example, json for data handling). 2. **Bedrock Configuration:** * `boto3.client('bedrock-runtime', ...)`: Creates a Bedrock client. **Crucially, replace `'your-aws-region'` with your AWS region (e.g., `'us-east-1'`) and `'your-bedrock-endpoint-url'` with your Bedrock endpoint URL if needed.** The endpoint URL is usually only needed if you're using a custom endpoint or a specific Bedrock feature. * `model_id`: Specifies the Bedrock model to use (e.g., `'anthropic.claude-v2'`). **Change this to the model you want to use.** See the Bedrock documentation for available models. 3. **MCP Server (Flask Example):** * `@app.route('/process_message', methods=['POST'])`: Defines a route that listens for POST requests at `/process_message`. This simulates your MCP server receiving a message. * `request.get_json()`: Parses the JSON data from the incoming request. **Adapt this to how your MCP server sends data.** * `user_message = data.get('message')`: Extracts the user's message from the JSON data. **Adjust the key (`'message'`) to match the structure of your MCP server's messages.** 4. **`invoke_bedrock(prompt)` Function:** * Constructs the JSON payload for the Bedrock API. The payload includes: * `prompt`: The user's message (the text you want Bedrock to process). * `max_tokens_to_sample`: The maximum number of tokens Bedrock should generate in its response. Adjust this based on the expected length of the response. * `temperature`: Controls the randomness of the output. Higher values (e.g., 0.7) produce more random and creative results. Lower values (e.g., 0.2) produce more predictable results. * `top_p`: Another parameter that controls randomness. It's often used in conjunction with `temperature`. * `bedrock.invoke_model(...)`: Calls the Bedrock API. * Parses the JSON response from Bedrock and extracts the `completion` (the generated text). * Includes error handling. 5. **Response Formatting:** * `formatted_response`: Creates a dictionary containing the Bedrock response and the original message. **Adapt this to the format your MCP server expects.** You might need to include user IDs, timestamps, or other metadata. 6. **Sending the Response:** * `return jsonify(formatted_response), 200`: Returns the formatted response as JSON. **In a real MCP server, you would send this response to the appropriate API endpoint to deliver it to the user.** This might involve using a different library (e.g., `requests` to make an HTTP request to your MCP server). 7. **Error Handling:** The code includes `try...except` blocks to catch potential errors (e.g., network issues, invalid JSON). **To Run This Example:** 1. **Install Dependencies:** ```bash pip install boto3 flask ``` 2. **Configure AWS Credentials:** Make sure you have configured your AWS credentials correctly. The easiest way is usually to use the AWS CLI: ```bash aws configure ``` You'll need an AWS account with access to Bedrock. You might need to request access to specific models in the Bedrock console. 3. **Replace Placeholders:** Replace the placeholder values for `your-aws-region`, `your-bedrock-endpoint-url`, and `model_id`. 4. **Run the Script:** ```bash python your_script_name.py ``` 5. **Test the Endpoint:** You can test the endpoint using `curl` or a tool like Postman: ```bash curl -X POST -H "Content-Type: application/json" -d '{"message": "Tell me a short story about a cat."}' http://localhost:5000/process_message ``` **Important Considerations:** * **Security:** If you're deploying this to a production environment, make sure to secure your MCP server and Bedrock API calls. Use appropriate authentication and authorization mechanisms. * **Error Handling:** Implement robust error handling to gracefully handle failures and provide informative error messages. * **Rate Limiting:** Be aware of Bedrock's rate limits and implement appropriate rate limiting in your code to avoid being throttled. * **Cost:** Bedrock usage can incur costs. Monitor your usage and set budgets to avoid unexpected charges. * **Asynchronous Processing:** For high-volume applications, consider using asynchronous processing (e.g., with Celery or AWS SQS) to avoid blocking the MCP server while waiting for Bedrock responses. * **MCP Server Integration:** The most important part is adapting the code to your specific MCP server's API. You'll need to understand how to receive messages from the server, how to format responses, and how to send responses back to the server. **Korean Translation (of the important parts):** * **`your-aws-region`**: 본인의 AWS 리전으로 변경하세요 (예: `us-east-1`). * **`your-bedrock-endpoint-url`**: 필요하다면 본인의 Bedrock 엔드포인트 URL로 변경하세요. * **`model_id`**: 사용하고 싶은 Bedrock 모델 ID로 변경하세요 (예: `anthropic.claude-v2`). Bedrock 문서에서 사용 가능한 모델을 확인하세요. * **MCP 서버 API에 맞게 코드를 조정해야 합니다.** 메시지를 받는 방법, 응답을 포맷하는 방법, 응답을 다시 서버로 보내는 방법을 이해해야 합니다. * **보안:** 프로덕션 환경에 배포하는 경우 MCP 서버와 Bedrock API 호출을 안전하게 보호해야 합니다. 적절한 인증 및 권한 부여 메커니즘을 사용하십시오. * **요금:** Bedrock 사용에는 비용이 발생할 수 있습니다. 사용량을 모니터링하고 예기치 않은 요금이 발생하지 않도록 예산을 설정하십시오. This comprehensive example should give you a solid starting point for integrating Gen-AI (Bedrock) with your MCP server. Remember to adapt the code to your specific requirements and environment. Good luck!

xserver-files-mcp

A local stdio MCP server for managing files on XServer via SFTP, enabling secure file operations, backups, and workspace management for XServer hosting.

Black Orchid

A hot-reloadable MCP proxy server that enables users to create and manage custom Python tools through dynamic module loading. Users can build their own utilities, wrap APIs, and extend functionality by simply adding Python files to designated folders.

codex-antigravity-bridge

Enables MCP-compatible clients like Codex to delegate tasks to the Antigravity CLI, using ConPTY on Windows to reliably capture responses.

spotify-mcp-server

Enables natural language control of Spotify, including search, playback, and device management, with robust error handling and automatic token refresh.

bunpro-mcp

An unofficial MCP server for Bunpro that exposes its review queue, search, statistics, and SRS management as tools, enabling an LLM agent to read study data and add grammar points or vocabulary to reviews.

remote-mcp-server-authless

A stateless remote MCP server on Cloudflare Workers without authentication, supporting custom tools and compatibility with legacy clients. Enables deployment and connection from remote MCP clients like Cloudflare AI Playground and Claude Desktop.

Magic Meal Kits MCP

Enables AI assistants to check the Magic Meal Kits server version through a single tool.

pdf-letter-mcp

Local MCP server that generates print-ready PDF letters with DIN 5008 compliant address positioning for window envelopes, handling structured content offline without external APIs.

MCP Memory

Enables AI assistants to remember user information and preferences across conversations using vector search technology. Built on Cloudflare infrastructure with isolated user namespaces for secure, persistent memory storage.

EMMA MCP

A custom MCP server that enables Claude to access and query municipal bond data from the MSRB's EMMA website, which lacks a public API. It provides 18 tools for searching bonds, downloading official statements, and extracting financial data through natural language prompts.

Prefeitura PE Recife: CPOM

Enables querying official data from the Prefeitura de Recife (Recife City Hall) through a hosted, read-only MCP server. Supports MCP over HTTP with usage-based prepaid billing.

carly-cli

Agent-native MCP server for Carly, the AI scheduling assistant. Exposes 11 tools to read and manage booking pages, event types, calendars, bookings, and available slots. Allows you to manage and create booking pages from the command line.

Jira Prompts MCP Server

Jira 콘텐츠로부터 프롬프트 또는 컨텍스트를 생성하는 여러 명령어를 제공하는 MCP 서버

Medical MCP Chatbot

A FastAPI backend service that connects to Azure's Managed Chat Project using GPT-4o to provide medical chatbot functionality through a simple HTML interface.

SEFAZ CE: Certidão Negativa de Débitos MCP

Enables querying SEFAZ Ceará tax clearance certificates (Certidão Negativa de Débitos) from official sources, read-only.

Sapphire Wellness MCP Server

A Python MCP server that exposes health metrics from the Sapphire Wellness App to AI assistants, providing tools for activity, blood pressure, glucose, heart rate, sleep, and SpO2 data.

MariaDB MCP Server

Enables querying local MariaDB and MySQL databases with optimized output formats designed to significantly reduce token consumption. It provides secure tools for exploring schemas and executing read-only SQL queries while automatically blocking destructive commands.

MCP Doctor

A diagnostic tool that evaluates the contract quality of MCP servers across dimensions like safety, efficiency, and documentation to provide actionable improvements. It helps developers ensure their servers are optimized for human users, distribution platforms, and AI agents.

app.wishpool/italy-payments-mcp

Lets AI agents accept payments in Italy via Stripe hosted checkout, supporting cards, Apple Pay, Google Pay, and Klarna. It provides tools to create payment links and query payment status.

bridge-mcp-server

Connects Ignition SCADA and Studio 5000 PLC to correlate tags end-to-end, trace signal chains, and find commissioning gaps.

gha-intel-mcp

MCP server that analyzes GitHub Actions workflow performance, audits configuration for optimization, and provides billing and cache usage insights.

ShopOracle

E-Commerce Intelligence MCP Server — 11 tools for product search, price comparison, competitor pricing across Amazon, eBay, Google Shopping. 18 countries. Part of ToolOracle (tooloracle.io).

gemot

Deliberation primitive for multi-agent coordination — agents submit positions, vote on a 5-point scale, and the server returns crux detection, vote clustering, bridging statements, and consensus. Inspired by Polis and Talk to the City.