Discover Awesome MCP Servers

Extend your agent with 84,517 capabilities via MCP servers.

All84,517
ggui

ggui

Enables AI agents to generate and serve ephemeral, interactive user interfaces over MCP through natural language descriptions.

BenchClaw MCP Server

BenchClaw MCP Server

Register LLMs and agents on the P2PCLAW decentralized benchmark network and query live performance scores via the BenchClaw API.

sql-assistant-mcp

sql-assistant-mcp

A Model Context Protocol (MCP) server for SQL Server / Azure SQL that enables querying, monitoring, and analyzing databases directly from Claude.

Athena MCP

Athena MCP

An MCP server that provides a reasoning sidekick for tool-using agents with a single 'think' tool for tackling complex problems. It allows agents to consult powerful reasoning models like Claude Opus or GPT-5 only when needed, keeping costs low while maintaining control over side effects.

agentbill-mcp

agentbill-mcp

MCP server for AI agent billing. Preflight spend checks before agent runs. Post-execution usage billing via two MCP tools: preflight() and record_event().

node-opcua-modeler-mcp-server

node-opcua-modeler-mcp-server

Provides AI agents with offline access to OPC UA companion specification types, dependencies, and engineering units for industrial modeling.

AndroidBuildMCP

AndroidBuildMCP

Enables AI agents to build, deploy, drive, and debug Android apps — managing Gradle builds, emulators, adb deployment, logcat capture, and full UI automation.

MCPCloud

MCPCloud

A self-hosted MCP gateway that lets you write Python functions and register them as skills to be used as tools by any MCP-compatible client like Claude Desktop or Claude API.

MCP server for Azure Cosmos DB using the Go SDK

MCP server for Azure Cosmos DB using the Go SDK

## Cosmos DB MCP Server Implementation (Go SDK) - Sample This is a sample implementation of an MCP (Management Control Plane) server for Cosmos DB using the Go SDK. This example focuses on basic container management (create, read, update, delete). It's a simplified illustration and requires further development for production use, including proper error handling, authentication, authorization, and more robust configuration. **Important Considerations:** * **Security:** This example lacks proper authentication and authorization. Implement robust security measures before deploying to a production environment. * **Error Handling:** Error handling is minimal. Implement comprehensive error handling and logging. * **Configuration:** Configuration is hardcoded. Use environment variables or a configuration file for flexibility. * **Scalability:** This is a single-instance server. Consider scalability strategies for production deployments. * **Idempotency:** Ensure operations are idempotent to handle retries gracefully. * **Monitoring:** Implement monitoring and alerting. **Code Structure:** The code is structured into the following parts: 1. **Dependencies:** Imports the necessary Go packages. 2. **Configuration:** Defines configuration parameters (Cosmos DB endpoint, key, database name). 3. **Cosmos DB Client:** Initializes the Cosmos DB client. 4. **Data Structures:** Defines data structures for representing container information. 5. **API Handlers:** Implements HTTP handlers for container management operations (create, read, update, delete). 6. **Main Function:** Sets up the HTTP server and starts listening for requests. **Code:** ```go package main import ( "context" "encoding/json" "fmt" "log" "net/http" "os" "github.com/Azure/azure-sdk-for-go/sdk/azidentity" "github.com/Azure/azure-sdk-for-go/sdk/data/azcosmos" ) // Configuration const ( cosmosDBEndpointEnvVar = "COSMOS_ENDPOINT" cosmosDBKeyEnvVar = "COSMOS_KEY" databaseName = "mcpdb" // Replace with your database name ) // ContainerInfo represents the structure for container information. type ContainerInfo struct { ID string `json:"id"` PartitionKey string `json:"partitionKey"` Throughput int `json:"throughput"` } var ( cosmosClient *azcosmos.Client databaseClient *azcosmos.DatabaseClient ) func main() { // 1. Initialize Cosmos DB client var err error cosmosClient, err = initializeCosmosClient() if err != nil { log.Fatalf("Failed to initialize Cosmos DB client: %v", err) } // 2. Get Database Client databaseClient, err = getDatabaseClient(cosmosClient, databaseName) if err != nil { log.Fatalf("Failed to get database client: %v", err) } // 3. HTTP Handlers http.HandleFunc("/containers", containerHandler) http.HandleFunc("/containers/", containerHandler) // For specific container operations // 4. Start HTTP Server port := ":8080" fmt.Printf("Server listening on port %s\n", port) log.Fatal(http.ListenAndServe(port, nil)) } func initializeCosmosClient() (*azcosmos.Client, error) { // Retrieve Cosmos DB endpoint and key from environment variables cosmosDBEndpoint := os.Getenv(cosmosDBEndpointEnvVar) cosmosDBKey := os.Getenv(cosmosDBKeyEnvVar) if cosmosDBEndpoint == "" || cosmosDBKey == "" { return nil, fmt.Errorf("Cosmos DB endpoint and key must be set in environment variables") } // Create a Cosmos DB client using the key credential. cred, err := azcosmos.NewKeyCredential(cosmosDBKey) if err != nil { return nil, fmt.Errorf("failed to create key credential: %w", err) } options := &azcosmos.ClientOptions{} client, err := azcosmos.NewClient(cosmosDBEndpoint, cred, options) if err != nil { return nil, fmt.Errorf("failed to create cosmos client: %w", err) } return client, nil } func getDatabaseClient(client *azcosmos.Client, databaseName string) (*azcosmos.DatabaseClient, error) { databaseClient, err := client.NewDatabase(databaseName) if err != nil { return nil, fmt.Errorf("failed to get database client: %w", err) } return databaseClient, nil } func containerHandler(w http.ResponseWriter, r *http.Request) { switch r.Method { case http.MethodPost: createContainer(w, r) case http.MethodGet: getContainer(w, r) // Get a specific container or list all case http.MethodPut: updateContainer(w, r) case http.MethodDelete: deleteContainer(w, r) default: http.Error(w, "Method not allowed", http.StatusMethodNotAllowed) } } func createContainer(w http.ResponseWriter, r *http.Request) { var containerInfo ContainerInfo err := json.NewDecoder(r.Body).Decode(&containerInfo) if err != nil { http.Error(w, err.Error(), http.StatusBadRequest) return } // Create container options options := &azcosmos.CreateContainerOptions{} // Set throughput if provided if containerInfo.Throughput > 0 { throughputProperties := azcosmos.NewManualThroughputProperties(containerInfo.Throughput) options.ThroughputProperties = &throughputProperties } // Create container properties containerProperties := azcosmos.ContainerProperties{ ID: containerInfo.ID, PartitionKeyDefinition: azcosmos.PartitionKeyDefinition{ Kind: azcosmos.PartitionKeyKindHash, Paths: []string{"/" + containerInfo.PartitionKey}, Version: azcosmos.PartitionKeyDefinitionVersionV2, }, } // Create the container ctx := context.TODO() containerResponse, err := databaseClient.CreateContainer(ctx, containerProperties, options) if err != nil { http.Error(w, fmt.Sprintf("Error creating container: %v", err), http.StatusInternalServerError) return } w.WriteHeader(http.StatusCreated) json.NewEncoder(w).Encode(containerResponse.ContainerProperties) } func getContainer(w http.ResponseWriter, r *http.Request) { containerID := r.URL.Path[len("/containers/"):] // Extract container ID from URL if containerID == "" { // List all containers (basic implementation) pager := databaseClient.NewListContainersPager(nil) var containerList []azcosmos.ContainerProperties for pager.More() { resp, err := pager.NextPage(context.TODO()) if err != nil { http.Error(w, fmt.Sprintf("Error listing containers: %v", err), http.StatusInternalServerError) return } containerList = append(containerList, resp.ContainerProperties...) } w.Header().Set("Content-Type", "application/json") json.NewEncoder(w).Encode(containerList) return } // Get a specific container containerClient, err := databaseClient.NewContainer(containerID) if err != nil { http.Error(w, fmt.Sprintf("Error getting container client: %v", err), http.StatusInternalServerError) return } resp, err := containerClient.Read(context.TODO(), nil) if err != nil { http.Error(w, fmt.Sprintf("Error reading container: %v", err), http.StatusNotFound) return } w.Header().Set("Content-Type", "application/json") json.NewEncoder(w).Encode(resp.ContainerProperties) } func updateContainer(w http.ResponseWriter, r *http.Request) { containerID := r.URL.Path[len("/containers/"):] // Extract container ID from URL if containerID == "" { http.Error(w, "Container ID is required for update", http.StatusBadRequest) return } var containerInfo ContainerInfo err := json.NewDecoder(r.Body).Decode(&containerInfo) if err != nil { http.Error(w, err.Error(), http.StatusBadRequest) return } // Get the container client containerClient, err := databaseClient.NewContainer(containerID) if err != nil { http.Error(w, fmt.Sprintf("Error getting container client: %v", err), http.StatusInternalServerError) return } // Update throughput (example) if containerInfo.Throughput > 0 { throughputProperties := azcosmos.NewManualThroughputProperties(containerInfo.Throughput) _, err = containerClient.ReplaceThroughput(context.TODO(), throughputProperties, nil) if err != nil { http.Error(w, fmt.Sprintf("Error updating throughput: %v", err), http.StatusInternalServerError) return } w.WriteHeader(http.StatusOK) w.Write([]byte("Throughput updated successfully")) return } http.Error(w, "No update operation specified", http.StatusBadRequest) } func deleteContainer(w http.ResponseWriter, r *http.Request) { containerID := r.URL.Path[len("/containers/"):] // Extract container ID from URL if containerID == "" { http.Error(w, "Container ID is required for deletion", http.StatusBadRequest) return } // Get the container client containerClient, err := databaseClient.NewContainer(containerID) if err != nil { http.Error(w, fmt.Sprintf("Error getting container client: %v", err), http.StatusInternalServerError) return } // Delete the container _, err = containerClient.Delete(context.TODO(), nil) if err != nil { http.Error(w, fmt.Sprintf("Error deleting container: %v", err), http.StatusInternalServerError) return } w.WriteHeader(http.StatusOK) w.Write([]byte("Container deleted successfully")) } ``` **Explanation:** 1. **Dependencies:** Imports necessary packages, including the Azure Cosmos DB Go SDK. 2. **Configuration:** Defines constants for the Cosmos DB endpoint, key, and database name. **Important:** These should be read from environment variables or a configuration file in a real-world application. The code uses `os.Getenv` to retrieve these values. 3. **Cosmos DB Client Initialization:** The `initializeCosmosClient` function creates a Cosmos DB client using the provided endpoint and key. It uses `azcosmos.NewKeyCredential` for authentication. Error handling is included. 4. **Database Client Initialization:** The `getDatabaseClient` function creates a Cosmos DB database client using the Cosmos DB client and the database name. 5. **Data Structures:** The `ContainerInfo` struct represents the structure of the container information that will be sent in the request body. 6. **API Handlers:** * `containerHandler`: This is the main handler for the `/containers` endpoint. It uses a `switch` statement to route requests based on the HTTP method (POST, GET, PUT, DELETE). * `createContainer`: Handles POST requests to create a new container. It decodes the JSON request body into a `ContainerInfo` struct, creates the container using the Cosmos DB SDK, and returns a success or error response. It also handles setting the throughput if provided in the request. * `getContainer`: Handles GET requests to retrieve container information. If a container ID is provided in the URL (e.g., `/containers/mycontainer`), it retrieves the information for that specific container. If no container ID is provided (e.g., `/containers`), it lists all containers in the database. * `updateContainer`: Handles PUT requests to update an existing container. It extracts the container ID from the URL and decodes the JSON request body. The example shows how to update the throughput of a container. * `deleteContainer`: Handles DELETE requests to delete a container. It extracts the container ID from the URL and deletes the container using the Cosmos DB SDK. 7. **Main Function:** * Initializes the Cosmos DB client. * Registers the API handlers with the HTTP server. * Starts the HTTP server on port 8080. **How to Run:** 1. **Install Go:** Make sure you have Go installed and configured. 2. **Install Dependencies:** Run `go get github.com/Azure/azure-sdk-for-go/sdk/azidentity github.com/Azure/azure-sdk-for-go/sdk/data/azcosmos` to install the necessary dependencies. 3. **Set Environment Variables:** Set the `COSMOS_ENDPOINT` and `COSMOS_KEY` environment variables to your Cosmos DB endpoint and key. 4. **Run the Server:** Run `go run main.go`. **Example Usage (using `curl`):** * **Create a Container:** ```bash curl -X POST -H "Content-Type: application/json" -d '{"id": "mycontainer", "partitionKey": "city", "throughput": 400}' http://localhost:8080/containers ``` * **Get a Container:** ```bash curl http://localhost:8080/containers/mycontainer ``` * **List All Containers:** ```bash curl http://localhost:8080/containers ``` * **Update Container Throughput:** ```bash curl -X PUT -H "Content-Type: application/json" -d '{"throughput": 600}' http://localhost:8080/containers/mycontainer ``` * **Delete a Container:** ```bash curl -X DELETE http://localhost:8080/containers/mycontainer ``` **Key Improvements and Next Steps:** * **Authentication and Authorization:** Implement proper authentication (e.g., API keys, JWT) and authorization to control access to the MCP server. * **Error Handling:** Implement more robust error handling, including logging and custom error responses. * **Configuration Management:** Use a configuration file or environment variables to manage configuration parameters. * **Input Validation:** Validate the input data to prevent errors and security vulnerabilities. * **Idempotency:** Ensure that operations are idempotent so that they can be retried safely. * **Monitoring and Logging:** Implement monitoring and logging to track the health and performance of the MCP server. * **Asynchronous Operations:** Consider using asynchronous operations for long-running tasks. * **More Container Management Features:** Add support for other container management features, such as updating container properties, managing indexing policies, and managing stored procedures. * **Database Management:** Extend the MCP to manage databases as well. * **Use Managed Identity:** Instead of using a key, use a managed identity for authentication in Azure environments. This is more secure. You'll need to use `azidentity.NewDefaultAzureCredential` and configure the Cosmos DB account to allow access from the managed identity. This sample provides a starting point for building a Cosmos DB MCP server using the Go SDK. Remember to address the security and error handling considerations before deploying to a production environment.

mcp-arcgis-houston

mcp-arcgis-houston

This MCP server provides access to City of Houston GIS open geospatial data, enabling search, query, and schema retrieval of datasets like parcels and zoning through ArcGIS feature services.

livewire-flux-mcp

livewire-flux-mcp

MCP server that provides access to Livewire Flux components and layouts documentation, enabling AI assistants to fetch and search through documentation on demand.

Google Workspace MCP Server

Google Workspace MCP Server

A comprehensive integration providing 114 tools to manage Google Drive, Docs, Sheets, Slides, Gmail, Calendar, and more through the Model Context Protocol. It enables seamless interaction with the full Google Workspace suite for file management, communication, and scheduling directly within Claude.

xrpldashboard MCP

xrpldashboard MCP

Read-only XRP Ledger analytics — signed snapshots, AMM pools, token volume, whale activity, NFT tracking. Proof-annotated. Public beta 2026-09.

Lokha MCP Server

Lokha MCP Server

A Model Context Protocol server hosted on Cloudflare Workers that integrates AI assistants with the Lokha ecosystem, currently providing Ghost CMS tools for content management, publishing, and scheduling.

SQL MCP Server Demo

SQL MCP Server Demo

Provides read-only access to SQL Server databases via Data API Builder, with tools to describe entities, read records, and aggregate data through the Model Context Protocol.

mcpappwrite

mcpappwrite

A minimal Python MCP Todo server backed by Appwrite Cloud, providing tools to add, list, get, update, complete, and delete tasks.

arcgis-grandchute

arcgis-grandchute

Enables AI agents to search and query Town of Grand Chute, Wisconsin open geospatial datasets (parcels, zoning, public works) via ArcGIS Feature Services.

MCP Utility Server

MCP Utility Server

A beginner-friendly MCP server offering time, math, internet quotes, dad jokes, file tools, web search, and optional LangChain agent.

MCP Standardized Tool Demo

MCP Standardized Tool Demo

A Node.js-based MCP server that extracts numbers from text and generates statistical chart data such as bar, pie, and line charts based on frequency. It enables AI agents to perform data extraction and visualization tasks through the Model Context Protocol.

Company Records

Company Records

Exposes a fictional B2B CRM database (companies, contacts, deals) as callable MCP tools, enabling AI agents to answer natural-language questions about company records, contacts, and pipeline data.

nstbrowser-playwright-mcp

nstbrowser-playwright-mcp

Combines NSTBrowser profile management with Playwright browser automation via CDP, enabling browser automation through NSTBrowser profiles.

keygenix-mcp

keygenix-mcp

Non-custodial TEE key management and signing for AI agents, supporting multiple blockchains.

forcedream-mcp

forcedream-mcp

Enables discovery and invocation of AI agents from the ForceDream platform. Provides cryptographic verification of agent outputs for trustless task integrity.

Web Search MCP Server

Web Search MCP Server

Provides web search capabilities using the Tavily API, enabling AI models to search the internet and retrieve up-to-date information.

Open Video Guide MCP Server

Open Video Guide MCP Server

Exposes Open Video Guide functions to MCP clients, enabling conversion of tutorial videos into illustrated, verifiable guides with timestamps, evidence, and review states.

telegram-mcp

telegram-mcp

Connects AI tools to Telegram via MCP, enabling reading chats, sending messages, managing groups, and more using your own account.

Google Workspace MCP Server

Google Workspace MCP Server

Enables AI agents to send emails via Gmail and append text to Google Docs through the Model Context Protocol.

Tracker MCP Server

Tracker MCP Server

Enables AI agents to manage Kanban boards, cards, sessions, and automations through a unified MCP interface with real-time updates, supporting delegation, agent sessions, and human-in-the-loop interactions.

video-watcher-mcp

video-watcher-mcp

An MCP server that lets Claude Desktop watch videos from YouTube, Instagram, Facebook, or direct URLs, extracting transcripts and key frames to summarize and answer questions about video content.

Aleph

Aleph

Enables AI assistants to analyze documents larger than their context window by loading files into RAM and querying them via search, navigation, and Python execution tools. Supports recursive reasoning to process massive datasets in chunks using sub-agents.