Discover Awesome MCP Servers

DeFi Rates MCP Server

Provides AI assistants with access to real-time DeFi lending rates and yield data across 14+ protocols and multiple blockchains. Enables querying borrow/supply rates, comparing platforms, calculating leverage strategies, and finding best earn opportunities.

Brave Search MCP Server

Một máy chủ MCP tích hợp API Brave Search để cung cấp cả khả năng tìm kiếm trên web và cục bộ, với các tính năng như phân trang, lọc và dự phòng thông minh.

MCP Antigravity Bridge

Enables OpenClaw agents to delegate complex coding tasks to the Antigravity VS Code environment via a filesystem-based mailbox system. It provides tools to submit tasks, monitor execution status, and retrieve results directly within the development workflow.

mcp-postgres

Enables AI agents to interact with PostgreSQL databases through schema intelligence, query execution, and DBA tooling including index analysis and health monitoring. Features configurable access levels and audit logging for secure database operations.

Big Brain MCP

Một máy chủ MCP thu thập số liệu thống kê từ các giao thức hàng đầu trong Mạng Mantle để giúp người dùng đưa ra quyết định đầu tư sáng suốt hơn.

Code Execution Server

Enables execution of code in a sandbox environment with integrated web search capabilities. Provides a basic framework for running code safely, primarily designed for AI agents and research applications.

DB Analytics & Query Platform

A FastAPI-based server that enables executing SQL queries, managing database connections, and retrieving analytics reports through MCP-integrated endpoints. It allows users to interact with database schemas, performance metrics, and access logs using structured queries.

mac-use-mcp

Zero-dependency macOS desktop automation for AI agents. Screenshot, mouse, keyboard, clipboard, and window control via MCP. 18 tools, macOS 13+, one command: npx mac-use-mcp.

DICOM-MCP

Một máy chủ Giao thức Bối cảnh Mô hình (Model Context Protocol) cho phép làm việc với hình ảnh y tế DICOM thông qua một hệ thống lưu trữ ghi chú đơn giản.

plsreadme

MCP server for sharing markdown/text as beautiful, permanent web pages via plsreadme, with tools to share files/text, update and delete docs, and list previously shared links.

GSC MCP Server v2 - Remote Edition

Connects Claude AI to Google Search Console with OAuth 2.0 authentication, enabling users to analyze search performance, inspect URLs, manage sitemaps, and export analytics data through natural language conversations.

Self-Hosted EdgeOne Pages MCP Server

Enables AI assistants to deploy and manage static websites directly on EdgeOne Pages. Simple self-hosted solution with one-click deployment and KV storage for website files.

FastMail MCP Server

Enables AI-powered email management through FastMail's JMAP API with features like smart email analysis, automated organization, inbox zero automation, and intelligent reply generation. Supports advanced email operations, contact management, calendar integration, and hierarchical email organization systems.

Gemini MCP Server

Một triển khai máy chủ MCP cho phép sử dụng các mô hình AI Gemini của Google (đặc biệt là Gemini 1.5 Pro) thông qua Claude hoặc các máy khách MCP khác thông qua Giao thức Ngữ cảnh Mô hình (Model Context Protocol).

Mcp Qdrant Docker

Okay, I can help you with a Docker configuration for a Qdrant MCP (Multi-Cluster Proxy) server. Here's a breakdown of what you'll need and a sample `docker-compose.yml` file, along with explanations to help you customize it for your specific needs. **Understanding the Components** * **Qdrant MCP (Multi-Cluster Proxy):** This is the component that sits in front of your Qdrant clusters. It handles routing requests to the appropriate cluster based on your configuration. It's essential for managing multiple Qdrant instances, especially in production environments. * **Docker:** Docker allows you to package and run the Qdrant MCP in a container, ensuring consistency and portability. * **Docker Compose (Recommended):** Docker Compose is a tool for defining and managing multi-container Docker applications. It simplifies the process of setting up and running the Qdrant MCP along with any necessary dependencies. **Key Considerations** 1. **Qdrant Cluster Endpoints:** You *must* know the addresses (hostnames or IP addresses and ports) of your existing Qdrant clusters. The MCP needs this information to route requests. 2. **Routing Configuration:** You'll need to define how the MCP should route requests to different clusters. This is typically based on collection names or other criteria. 3. **Ports:** Choose a port for the MCP to listen on for incoming requests. Make sure this port is accessible from your applications. 4. **Volumes (Optional but Recommended for Persistence):** If you want to persist the MCP's configuration (e.g., routing rules), you should use Docker volumes to store the configuration file. 5. **Environment Variables:** Use environment variables to configure the MCP, such as the port it listens on and the path to the configuration file. 6. **Health Checks:** Implement health checks in your Docker Compose file to ensure the MCP is running correctly. **Example `docker-compose.yml`** ```yaml version: "3.9" services: qdrant-mcp: image: qdrant/qdrant-mcp:latest # Use the latest MCP image container_name: qdrant-mcp ports: - "6334:6334" # Expose the MCP port (host:container) environment: QDRANT_MCP_CONFIG_PATH: /opt/qdrant-mcp/config/mcp_config.yaml # Path to the config file inside the container QDRANT_MCP_PORT: 6334 # Port the MCP listens on volumes: - ./mcp_config.yaml:/opt/qdrant-mcp/config/mcp_config.yaml # Mount the config file from your host restart: unless-stopped healthcheck: test: ["CMD", "curl", "-f", "http://localhost:6334/"] # Simple health check interval: 10s timeout: 5s retries: 3 networks: default: name: qdrant-network # Optional: Use a dedicated network for Qdrant components ``` **Explanation of the `docker-compose.yml`:** * **`version: "3.9"`:** Specifies the Docker Compose file version. * **`services:`:** Defines the services that make up your application. In this case, we have only one service: `qdrant-mcp`. * **`image: qdrant/qdrant-mcp:latest`:** Specifies the Docker image to use for the MCP. `qdrant/qdrant-mcp` is the official image. Using `:latest` pulls the most recent version, but for production, it's *highly recommended* to use a specific version tag (e.g., `qdrant/qdrant-mcp:v1.2.3`) to avoid unexpected breaking changes. * **`container_name: qdrant-mcp`:** Assigns a name to the container. * **`ports:`:** Maps ports from the host machine to the container. `6334:6334` means that port 6334 on your host machine will be forwarded to port 6334 inside the container. Change the host port if needed. * **`environment:`:** Sets environment variables for the container. * `QDRANT_MCP_CONFIG_PATH`: Specifies the path to the MCP configuration file *inside* the container. * `QDRANT_MCP_PORT`: Specifies the port the MCP listens on. This should match the container port in the `ports` section. * **`volumes:`:** Mounts volumes from the host machine to the container. This is crucial for persisting the MCP configuration. * `./mcp_config.yaml:/opt/qdrant-mcp/config/mcp_config.yaml`: This mounts the `mcp_config.yaml` file from the current directory on your host machine to the `/opt/qdrant-mcp/config/mcp_config.yaml` path inside the container. You'll need to create this `mcp_config.yaml` file (see below). * **`restart: unless-stopped`:** Configures the container to restart automatically unless it's explicitly stopped. This is a good practice for ensuring the MCP is always running. * **`healthcheck:`:** Defines a health check to verify that the MCP is running correctly. In this example, it uses `curl` to check if the MCP is responding to HTTP requests on port 6334. * **`networks:`:** (Optional) Defines a Docker network. Using a dedicated network for Qdrant components can improve security and isolation. **`mcp_config.yaml` (Example Configuration File)** This is the *most important* part. You need to create a `mcp_config.yaml` file in the same directory as your `docker-compose.yml` file. This file defines how the MCP routes requests to your Qdrant clusters. ```yaml clusters: cluster1: address: "qdrant-cluster-1:6333" # Replace with the actual address of your Qdrant cluster cluster2: address: "qdrant-cluster-2:6333" # Replace with the actual address of your Qdrant cluster routing: collection_mappings: my_collection_a: cluster1 # Route requests for "my_collection_a" to cluster1 my_collection_b: cluster2 # Route requests for "my_collection_b" to cluster2 default_cluster: cluster1 # Optional: If a collection isn't explicitly mapped, route to this cluster ``` **Explanation of `mcp_config.yaml`:** * **`clusters:`:** Defines the Qdrant clusters that the MCP will route requests to. * `cluster1`, `cluster2`: These are arbitrary names you give to your clusters. Use descriptive names. * `address`: The address (hostname or IP address and port) of the Qdrant cluster. *This is crucial and must be correct.* Make sure these addresses are resolvable from within the Docker container. If your Qdrant clusters are also running in Docker, use their service names within the same Docker network. * **`routing:`:** Defines how requests are routed to the clusters. * `collection_mappings:`: Maps collection names to specific clusters. When a request comes in for a collection listed here, it will be routed to the corresponding cluster. * `default_cluster:`: (Optional) Specifies a default cluster to route requests to if the collection name is not found in the `collection_mappings`. If you don't specify a `default_cluster` and a collection is not mapped, the MCP will return an error. **How to Run It** 1. **Create the `docker-compose.yml` and `mcp_config.yaml` files** in the same directory. *Make sure to replace the placeholder addresses in `mcp_config.yaml` with the actual addresses of your Qdrant clusters.* 2. **Open a terminal** in the directory where you created the files. 3. **Run `docker-compose up -d`** to start the MCP in detached mode (running in the background). 4. **Check the logs** with `docker-compose logs -f qdrant-mcp` to see if the MCP started successfully and to troubleshoot any issues. **Important Notes and Best Practices** * **Networking:** If your Qdrant clusters are also running in Docker, make sure they are on the same Docker network as the MCP. This allows the MCP to resolve the cluster addresses using their service names (e.g., `qdrant-cluster-1`). The `networks` section in the `docker-compose.yml` file helps with this. * **Configuration Reloading:** The Qdrant MCP typically requires a restart to pick up changes to the `mcp_config.yaml` file. Consider using a tool like `entr` or a similar file-watching mechanism to automatically restart the container when the configuration file changes. * **Security:** In a production environment, you should secure the MCP with authentication and authorization. Refer to the Qdrant MCP documentation for details on how to configure security. * **Monitoring:** Monitor the MCP's performance and health. You can use tools like Prometheus and Grafana to collect and visualize metrics. * **Logging:** Configure proper logging for the MCP to help with troubleshooting. * **Version Pinning:** *Always* use specific version tags for your Docker images in production (e.g., `qdrant/qdrant-mcp:v1.2.3`) instead of `latest`. This prevents unexpected breaking changes when the image is updated. * **Advanced Routing:** The `mcp_config.yaml` file can support more complex routing rules based on request headers, query parameters, or other criteria. Refer to the Qdrant MCP documentation for details. * **Qdrant Documentation:** The official Qdrant documentation is your best resource for the most up-to-date information on the MCP: [https://qdrant.tech/documentation/](https://qdrant.tech/documentation/) **Vietnamese Translation of Key Terms** * **Qdrant MCP (Multi-Cluster Proxy):** Qdrant MCP (Proxy Đa Cụm) * **Docker:** Docker * **Docker Compose:** Docker Compose * **Cluster:** Cụm * **Endpoint:** Điểm cuối * **Routing:** Định tuyến * **Configuration:** Cấu hình * **Port:** Cổng * **Volume:** Ổ đĩa ảo (trong Docker) * **Environment Variable:** Biến môi trường * **Health Check:** Kiểm tra sức khỏe * **Collection:** Bộ sưu tập (trong Qdrant) * **Image:** Ảnh (Docker image) * **Container:** Container (Docker container) * **Address:** Địa chỉ **Example Vietnamese Explanation** "Để cấu hình Docker cho Qdrant MCP (Proxy Đa Cụm), bạn cần tạo một file `docker-compose.yml` và một file cấu hình `mcp_config.yaml`. File `docker-compose.yml` sẽ định nghĩa cách chạy container Qdrant MCP, bao gồm việc chỉ định image Docker, cổng (port), biến môi trường (environment variable) và ổ đĩa ảo (volume) để lưu trữ file cấu hình. File `mcp_config.yaml` sẽ định nghĩa cách định tuyến (routing) các yêu cầu đến các cụm (cluster) Qdrant khác nhau, dựa trên tên bộ sưu tập (collection) hoặc các tiêu chí khác. Quan trọng nhất là bạn cần thay thế các địa chỉ (address) placeholder trong `mcp_config.yaml` bằng địa chỉ thực tế của các cụm Qdrant của bạn." This detailed explanation and example should give you a solid foundation for setting up a Qdrant MCP server using Docker. Remember to adapt the configuration to your specific environment and consult the official Qdrant documentation for more advanced features and options. Good luck!

Gitea MCP Proxy Agent

A comprehensive MCP server suite that enables AI interaction with Gitea for repository management, secure command execution, and Docker monitoring. It provides additional tools for long-term memory, filesystem access, and web searching to support full development cycles.

Coffee Company MCP Server

An MCP adapter that maps Coffee Company B2B HTTP APIs to MCP tools, allowing AI agents to query member information, benefits, coupons, and payment statuses. It enables seamless integration for AI assistants to manage coffee-related customer assets and loyalty details through natural language.

Google Ads MCP Server

Enables LLMs to interact with the Google Ads API to retrieve account information, list accessible customers, and query campaign performance. It allows users to manage and analyze Google Ads data through natural language interfaces.

MindLayer TradingView MCP Agent

Connects TradingView's Pine Script indicators with MindLayer's MCP for cryptocurrency trading signals based on RSI and Stochastic RSI analysis.

ARBuilder

AI-powered code generator for the Arbitrum ecosystem with 19 MCP tools. Generates Stylus smart contracts (Rust/WASM), SDK bridging code, full-stack dApps, and Orbit chain deployments using RAG-based retrieval over Arbitrum documentation.

Agile Luminary MCP Server

A Model Context Protocol server that connects AI clients to the Agile Luminary project management system, allowing users to retrieve project details, work assignments, and product information within AI conversations.

Deepgram MCP Server

Enables speech-to-text transcription, text-to-speech synthesis, and audio analysis using Deepgram's AI models. Supports features like speaker diarization, sentiment analysis, language detection, and various audio processing capabilities.

MCP Local File Reader

Enables comprehensive local file system operations including searching and reading content from various formats like PDF, Office documents, CSV, and text files. It features automatic character encoding detection and secure path validation for directory access.

FI-MCP

Provides AI assistants with access to 30+ validated financial independence calculation functions, eliminating hallucinations by ensuring accurate calculations for retirement planning, CoastFI, investment returns, and other FI metrics.

MCPDocSearch

Crawls documentation websites and provides semantic search capabilities over the content through vector embeddings, enabling natural language queries of technical documentation.

pterodactyl-mcp

MCP server for Pterodactyl and Pelican game server panels. 73 tools for server management, power control, file operations, backups, schedules, databases, users, nodes, and eggs.

Querysharp MCP Server

Enables AI assistants to analyze and optimize PostgreSQL database performance by identifying missing indexes and suggesting query rewrites. It allows users to retrieve database projects and implement performance fixes directly through natural language in their code editor.

ARGENTUM

Karma economy for AI agents and humans. Submit good actions, get community attestations, earn on-chain reputation. Karma-weighted verification, slashing, Kleros disputes. 5 MCP tools: submit_action, attest_action, get_karma, get_action_detail, get_leaderboard.

OpenAI Image Generation MCP Server

Provides tools for generating and editing images using OpenAI's gpt-image-1 model via an MCP interface, enabling AI assistants to create and modify images based on text prompts.