Discover Awesome MCP Servers

MythxEngine

Enables AI to act as Game Master for tabletop RPGs with deterministic dice, five-tier outcomes, FitD-style stress, combat tracking, clocks, investigations, NPC relationships, and world generation via 134 tools over MCP.

Domainnameregistration.com MCP

Enables fast, token-efficient bulk domain name search for AI agents, checking up to 1,000 domains per request to see availability statuses.

gsc-mcp-server

Enables Claude to access Google Search Console data including search performance, URL indexation, sitemaps, and built-in SEO analysis tools such as trending queries, cannibalization detection, and traffic drop diagnostics.

MCPDocSearch

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

Rodev MCP Server

Connects AI agents to Rodev DeFi vaults, enabling deposits, withdrawals, and status queries via 9 MCP tools.

Financial Data MCP Server

Provides real-time and historical financial market data from Yahoo Finance, including stock prices, options chains, and company news. It also enables technical analysis calculations like moving averages and RSI for comparing or analyzing stock performance.

Cymbal Catering MCP Server

Enables secure, natural language access to private Cloud SQL PostgreSQL data for catering CRM management, exposing database CRUD operations as MCP tools via Cloud Run.

MealPlanner MCP Multi-Agent

A multimodal meal planning agent that uses Gemini Vision to analyze fridge photos, suggest recipes, provide nutritional info, and generate daily meal plans.

LuzzyTool

A local smart tool collection based on MCP that enables AI assistants to perform file management, document editing, shell execution, semantic retrieval, and text processing.

LibreLink Up (CGM)

Read-only MCP server for accessing glucose readings, charts, logbook, and statistics from LibreLink Up sensors, supporting any MCP client.

Codecov MCP Server

Enables querying Codecov coverage data including file, commit, repository, and pull request coverage.

Heista MCP

Decode any video ad, load brand information, and generate ad scripts from inside MCP-compatible clients like Claude and ChatGPT.

video_agent

Enables probing, ingesting, transcribing, and searching Bilibili videos with timestamped evidence and frame extraction, without reading browser cookies.

dingdawg-healthcare-agent

Enables HIPAA-aware healthcare workflow automation including patient intake, clinical summaries, compliance checking, and appointment scheduling via MCP tools.

Mcp Qdrant Docker

Okay, here's a breakdown of Docker configuration for a Qdrant MCP (Multi-Cluster Proxy) server, along with explanations and best practices. I'll cover the key aspects: **1. Dockerfile (Example)** This is the foundation. It defines how your Docker image is built. ```dockerfile # Use an official Qdrant image as the base FROM qdrant/qdrant:latest # Or a specific version, e.g., qdrant/qdrant:v1.7.5 # Set environment variables (optional, but recommended) ENV QDRANT__SERVICE__GRPC_PORT=6333 ENV QDRANT__SERVICE__HTTP_PORT=6332 ENV QDRANT__CLUSTER__NODE_ID=mcp-node-1 # Unique ID for this MCP instance ENV QDRANT__CLUSTER__TYPE=mcp ENV QDRANT__CLUSTER__MCP__CLUSTER_URIS="qdrant-node-1:6333,qdrant-node-2:6333" # Comma-separated list of Qdrant cluster nodes ENV QDRANT__CLUSTER__MCP__REPLICATION_FACTOR=2 # Replication factor for the MCP ENV QDRANT__STORAGE__STORAGE_PATH=/qdrant/storage # Path for storage (important for persistence) # Expose ports (important for access) EXPOSE 6333 # gRPC port EXPOSE 6332 # HTTP port # Healthcheck (optional, but highly recommended) HEALTHCHECK --interval=30s --timeout=10s --retries=3 \ CMD curl -f http://localhost:6332/healthz || exit 1 # Command to start Qdrant (usually not needed, but can be customized) # CMD ["/usr/local/bin/qdrant", "--config-path", "/path/to/your/config.yaml"] # If you have a custom config file ``` **Explanation of Dockerfile Instructions:** * **`FROM qdrant/qdrant:latest`**: This line is crucial. It pulls the official Qdrant Docker image from Docker Hub. Using `latest` is convenient for quick testing, but **strongly consider using a specific version tag** (e.g., `qdrant/qdrant:v1.7.5`) for production to ensure consistent behavior and avoid unexpected updates. * **`ENV ...`**: Environment variables are the preferred way to configure Qdrant within Docker. Here's a breakdown of the key variables for an MCP setup: * `QDRANT__SERVICE__GRPC_PORT`: The gRPC port Qdrant will listen on. Defaults to 6333. * `QDRANT__SERVICE__HTTP_PORT`: The HTTP port Qdrant will listen on. Defaults to 6332. * `QDRANT__CLUSTER__NODE_ID`: A unique identifier for this Qdrant instance within the cluster. Make sure each node has a different ID. * `QDRANT__CLUSTER__TYPE=mcp`: Specifies that this instance is an MCP. * `QDRANT__CLUSTER__MCP__CLUSTER_URIS`: A comma-separated list of the gRPC addresses of the Qdrant nodes that this MCP will proxy to. The format is `hostname:port`. **Important:** These hostnames must be resolvable from within the Docker container. If your Qdrant nodes are running in the same Docker network, use their service names (e.g., `qdrant-node-1:6333`). If they are running on the host machine, you might need to use `host.docker.internal:6333` (on Docker Desktop) or configure your network accordingly. * `QDRANT__CLUSTER__MCP__REPLICATION_FACTOR`: The replication factor for the MCP. This determines how many underlying Qdrant nodes will store each data point. * `QDRANT__STORAGE__STORAGE_PATH`: The directory where Qdrant will store its data. **Very important for persistence!** You'll want to mount a Docker volume to this path to ensure that your data survives container restarts. * **`EXPOSE 6333 6332`**: This tells Docker that the container will listen on these ports. It's mostly for documentation and doesn't automatically publish the ports. You'll need to use the `-p` flag in `docker run` or the `ports` section in `docker-compose.yml` to actually map these ports to the host. * **`HEALTHCHECK`**: A health check is crucial for container orchestration. This command periodically checks if the Qdrant service is healthy by sending an HTTP request to the `/healthz` endpoint. If the request fails, the container is considered unhealthy, and your orchestrator (e.g., Docker Compose, Kubernetes) can take action (e.g., restart the container). * **`CMD ...`**: This specifies the command to run when the container starts. In most cases, you don't need to override the default command provided by the `qdrant/qdrant` image. However, if you have a custom configuration file, you can use this to specify its path. **2. Docker Compose (Example)** Docker Compose is a convenient way to define and manage multi-container Docker applications. Here's an example `docker-compose.yml` file for a Qdrant MCP setup with two Qdrant nodes: ```yaml version: "3.9" services: qdrant-node-1: image: qdrant/qdrant:latest container_name: qdrant-node-1 ports: - "6333:6333" - "6332:6332" environment: QDRANT__SERVICE__GRPC_PORT: 6333 QDRANT__SERVICE__HTTP_PORT: 6332 QDRANT__CLUSTER__NODE_ID: qdrant-node-1 QDRANT__STORAGE__STORAGE_PATH: /qdrant/storage volumes: - qdrant-node-1-data:/qdrant/storage networks: - qdrant-net qdrant-node-2: image: qdrant/qdrant:latest container_name: qdrant-node-2 ports: - "6334:6333" # Map host port 6334 to container port 6333 - "6335:6332" # Map host port 6335 to container port 6332 environment: QDRANT__SERVICE__GRPC_PORT: 6333 QDRANT__SERVICE__HTTP_PORT: 6332 QDRANT__CLUSTER__NODE_ID: qdrant-node-2 QDRANT__STORAGE__STORAGE_PATH: /qdrant/storage volumes: - qdrant-node-2-data:/qdrant/storage networks: - qdrant-net qdrant-mcp: image: qdrant/qdrant:latest container_name: qdrant-mcp ports: - "6336:6333" # Map host port 6336 to container port 6333 - "6337:6332" # Map host port 6337 to container port 6332 environment: QDRANT__SERVICE__GRPC_PORT: 6333 QDRANT__SERVICE__HTTP_PORT: 6332 QDRANT__CLUSTER__NODE_ID: qdrant-mcp QDRANT__CLUSTER__TYPE: mcp QDRANT__CLUSTER__MCP__CLUSTER_URIS: "qdrant-node-1:6333,qdrant-node-2:6333" QDRANT__CLUSTER__MCP__REPLICATION_FACTOR: 2 QDRANT__STORAGE__STORAGE_PATH: /qdrant/storage depends_on: - qdrant-node-1 - qdrant-node-2 networks: - qdrant-net volumes: qdrant-node-1-data: qdrant-node-2-data: networks: qdrant-net: driver: bridge ``` **Explanation of Docker Compose File:** * **`version: "3.9"`**: Specifies the Docker Compose file version. * **`services:`**: Defines the services (containers) that make up your application. * **`qdrant-node-1` and `qdrant-node-2`**: These are the two Qdrant nodes that the MCP will proxy to. * `image`: Uses the official Qdrant image. * `container_name`: Sets a name for the container. * `ports`: Maps ports from the host machine to the container. **Important:** In this example, I've mapped different host ports to the same container ports for each node. This is necessary because you can't have multiple containers binding to the same port on the host. Adjust these mappings as needed. * `environment`: Sets the environment variables for the Qdrant nodes. Note that each node has a unique `QDRANT__CLUSTER__NODE_ID`. * `volumes`: Mounts Docker volumes to the `/qdrant/storage` directory to persist data. * `networks`: Attaches the containers to a Docker network called `qdrant-net`. This allows the containers to communicate with each other using their service names as hostnames. * **`qdrant-mcp`**: This is the Qdrant MCP container. * `image`: Uses the official Qdrant image. * `container_name`: Sets a name for the container. * `ports`: Maps ports from the host machine to the container. * `environment`: Sets the environment variables for the Qdrant MCP. Crucially, `QDRANT__CLUSTER__TYPE` is set to `mcp`, and `QDRANT__CLUSTER__MCP__CLUSTER_URIS` points to the gRPC addresses of the Qdrant nodes. * `depends_on`: Ensures that the Qdrant nodes are started before the MCP. * `networks`: Attaches the container to the `qdrant-net` network. * **`volumes:`**: Defines the Docker volumes used for data persistence. * **`networks:`**: Defines the Docker network used for communication between the containers. **3. Building and Running** 1. **Create the Dockerfile and docker-compose.yml:** Save the code above into files named `Dockerfile` and `docker-compose.yml` in the same directory. 2. **Build the image (if needed):** If you've customized the Dockerfile, build the image: ```bash docker build -t qdrant-mcp . # The dot (.) means the current directory ``` 3. **Run with Docker Compose:** ```bash docker-compose up -d # -d runs in detached mode (background) ``` 4. **Check the logs:** ```bash docker-compose logs -f qdrant-mcp # Follow the logs of the MCP container docker-compose logs -f qdrant-node-1 docker-compose logs -f qdrant-node-2 ``` 5. **Stop the containers:** ```bash docker-compose down ``` **4. Important Considerations and Best Practices** * **Persistence:** The most critical aspect is data persistence. **Always mount Docker volumes to the `QDRANT__STORAGE__STORAGE_PATH` directory.** Without this, your data will be lost when the container is stopped or restarted. * **Networking:** Ensure that your Qdrant nodes and MCP can communicate with each other. Docker networks are the easiest way to achieve this. Use the service names as hostnames within the network. * **Resource Limits:** Consider setting resource limits (CPU, memory) for your containers using Docker Compose or Kubernetes. This prevents a single container from consuming all resources and potentially crashing the entire system. Example in `docker-compose.yml`: ```yaml services: qdrant-node-1: # ... other configurations deploy: resources: limits: cpus: '2' memory: 4G ``` * **Health Checks:** Implement health checks to ensure that your containers are running correctly. This allows your orchestrator to automatically restart unhealthy containers. * **Logging:** Configure proper logging for your Qdrant instances. Docker provides basic logging, but you might want to use a more advanced logging solution (e.g., ELK stack, Graylog) for production environments. * **Monitoring:** Monitor the performance of your Qdrant cluster using metrics. Qdrant exposes metrics in Prometheus format. You can use Prometheus and Grafana to visualize these metrics. * **Security:** * **Never expose your Qdrant ports directly to the internet without proper security measures.** Use a reverse proxy (e.g., Nginx, Traefik) with authentication and authorization. * Consider using TLS/SSL for communication between your Qdrant nodes and clients. * Regularly update your Qdrant images to the latest versions to patch security vulnerabilities. * **Configuration Management:** For complex deployments, consider using a configuration management tool (e.g., Ansible, Terraform) to automate the deployment and configuration of your Qdrant cluster. * **Kubernetes:** For production deployments, Kubernetes is highly recommended for its scalability, resilience, and management capabilities. There are Helm charts available for deploying Qdrant on Kubernetes. * **Version Pinning:** Always pin your Qdrant image versions (e.g., `qdrant/qdrant:v1.7.5`) in your Dockerfile and Docker Compose files. This ensures that you're using a consistent version of Qdrant and avoids unexpected behavior due to automatic updates. * **MCP Replication Factor:** The `QDRANT__CLUSTER__MCP__REPLICATION_FACTOR` determines how many underlying Qdrant nodes will store each data point. A higher replication factor provides better fault tolerance but also increases storage requirements. Choose a replication factor that is appropriate for your needs. * **Resource Allocation:** Carefully consider the resource requirements of your Qdrant nodes and MCP. Allocate enough CPU, memory, and storage to ensure that your cluster can handle your workload. Monitor resource usage and adjust as needed. **Japanese Translation of Key Phrases:** * Docker configuration: Docker の設定 (Docker no settei) * Qdrant MCP server: Qdrant MCP サーバー (Qdrant MCP sābā) * Dockerfile: Dockerfile (ドッカーファイル) * Docker Compose: Docker Compose (ドッカーコンポーズ) * Environment variables: 環境変数 (kankyō hensu) * Ports: ポート (pōto) * Volumes: ボリューム (boryūmu) * Networking: ネットワーク (nettowāku) * Persistence: 永続性 (eizokusei) * Health check: ヘルスチェック (herusu chekku) * Resource limits: リソース制限 (risōsu seigen) * Security: セキュリティ (sekyuriti) * Replication factor: レプリケーションファクター (repurikēshon fakutā) This comprehensive guide should help you configure a Qdrant MCP server using Docker. Remember to adapt the examples to your specific needs and environment. Good luck!

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.

Power Platform Pipeline MCP Server

Exposes Power Platform Pipeline operations as MCP tools for Copilot Studio agents, enabling pipeline discovery, deployments, approvals, and configuration management.

MCP Data Server

An MCP server that connects AI agents to cloud-native geospatial data via STAC metadata and DuckDB with H3 spatial indexing, enabling zero-configuration SQL queries on terabyte-scale datasets over S3.

tome-mcp

Manages a research paper library, providing PDF ingestion, bibliography management, semantic search, figure tracking, and integration with Semantic Scholar.

worldmonitor-mcp

MCP server wrapping worldmonitor global intelligence dashboard, exposing 140 tools across 32 services for live market, geopolitical, military, cyber, climate, and supply chain data.

obolpay-x402-mcp

MCP server for a live x402 payment gateway on Base (USDC). Lets AI agents discover, preview for free, then pay per call — with prepaid gasless payments, signed receipts, and delta delivery.

Singapore Location Intelligence MCP

Provides comprehensive Singapore transport routing with real-time public transport data, weather-aware journey planning, postal code resolution, and Google Maps-quality turn-by-turn navigation across MRT, LRT, buses, and walking routes.

PyMCPAutoGUI

AIエージェントとGUI自動化機能を連携させ、マウス、キーボード、ウィンドウの操作、スクリーンショットの取得を通じてデスクトップアプリケーションと対話できるMCPサーバー。

ICP Intelligence MCP

Enables deep ICP analysis with 9 tools for ideal customer profiling, market sizing, buyer mapping, and account prioritization.

appcrane-mcp

MCP connector for AppCrane that serves a bundled tool catalog for offline introspection and proxies tool calls to a self-hosted AppCrane instance for deploying and managing AI-built apps.

Arco Lexicon

Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authentication required. Streamable HTTP transport.

gl-mcp-feedback

A feedback-oriented MCP server with a Web UI for AI development workflows, enabling interactive confirmations and reducing speculative tool calls.

think-mcp

Provides structured thinking tools including mental models, design patterns, debugging approaches, decision frameworks, and multi-persona reasoning to enhance AI assistant problem-solving capabilities.

MongoDB That Works - MCP Server

Enables interaction with MongoDB databases through CRUD operations, aggregation, and schema discovery, with automatic field validation and ObjectId conversion.