Discover Awesome MCP Servers

Datadog MCP Server

Enables comprehensive Datadog monitoring capabilities including CI/CD pipeline management, service logs analysis, metrics querying, monitor and SLO management, service definitions retrieval, and team management through Claude and other MCP clients.

Brave Search

Web and local search using Brave's Search API

Permission Marketing MCP

Operationalizes Seth Godin's Permission Marketing framework to manage user trust and delegation in AI agent systems through a structured five-level permission ladder. It provides tools for requesting, auditing, and revoking permissions to enable autonomous agent actions within user-defined guardrails.

deeplook

Researches any company in ~10 seconds using 10 data sources. Returns structured reports with bull/bear verdict for stocks, crypto, and private companies.

Dexcom + Carb Search

Enables diabetes management by retrieving real-time glucose readings from Dexcom continuous glucose monitors and searching for carbohydrate content of foods to help make informed dietary decisions.

WordPress MCP Server

Cermin dari

Spotify MCP Server

Enables interaction with Spotify's music catalog through natural language conversations. Search for tracks and artists, get recommendations, explore playlists, and browse artist discographies using the Spotify Web API.

Wikidata MCP Server

Connects LLMs to Wikidata's structured knowledge base using a hybrid architecture that optimizes for both fast entity searches and complex relational queries. It provides tools for entity and property retrieval, metadata lookups, and direct SPARQL execution to ground AI responses in verified data.

GitHub Style Markdown Preview MCP App

Enables the previewing of GitHub Flavored Markdown (GFM) as an MCP application. It provides a tool to render and visualize Markdown content using authentic GitHub styling and CSS.

cortex-mcp

Calendar MCP server with atomic booking, conflict prevention, deterministic RRULE expansion, and TOON token compression for AI agents.

MCP Server F1Data

Enables interaction with Formula 1 data through LLM interfaces like Claude. Provides access to F1 information including circuits, constructors, drivers, grand prix, manufacturers, races, and seasons.

Hello Golang MCP

Berikut adalah implementasi server MCP Golang minimal dengan mcp-go: ```go package main import ( "context" "fmt" "log" "net" "os" "os/signal" "syscall" "google.golang.org/grpc" mcp "istio.io/api/mcp/v1alpha1" "istio.io/istio/pkg/mcp/server" "istio.io/istio/pkg/mcp/testing" ) const ( port = 18000 ) // SimpleSource implements the Source interface. type SimpleSource struct { // Resources to return. Resources map[string][]testing.Resource } // GetResources implements the Source interface. func (s *SimpleSource) GetResources(typeName string) ([]testing.Resource, error) { return s.Resources[typeName], nil } // GenerateSnapshot implements the Source interface. func (s *SimpleSource) GenerateSnapshot(versions map[string]string) (map[string]*mcp.Resources, error) { snapshot := map[string]*mcp.Resources{} for typeURL, resources := range s.Resources { res := &mcp.Resources{ VersionInfo: "1", // Simple version } for _, r := range resources { res.Resources = append(res.Resources, r.Resource) } snapshot[typeURL] = res } return snapshot, nil } // Watch implements the Source interface. func (s *SimpleSource) Watch(ctx context.Context, typeURL string, sink chan server.Event) error { // In a real implementation, this would watch for changes and send events to the sink. // For this example, we just send a single event with the current snapshot. snapshot, err := s.GenerateSnapshot(nil) if err != nil { return err } sink <- server.Event{ FullSync: true, Deltas: snapshot, } return nil } func main() { // Create a listener on TCP port lis, err := net.Listen("tcp", fmt.Sprintf(":%d", port)) if err != nil { log.Fatalf("failed to listen: %v", err) } // Create a gRPC server object s := grpc.NewServer() // Create a simple source with some example resources source := &SimpleSource{ Resources: map[string][]testing.Resource{ "type.googleapis.com/google.protobuf.StringValue": { { Name: "resource1", Resource: testing.CreateResource("resource1", "type.googleapis.com/google.protobuf.StringValue", []byte(`"value1"`)), }, { Name: "resource2", Resource: testing.CreateResource("resource2", "type.googleapis.com/google.protobuf.StringValue", []byte(`"value2"`)), }, }, }, } // Create the MCP server mcpServer := server.New(source) // Register the MCP server with the gRPC server mcp.RegisterAggregatedMeshConfigServiceServer(s, mcpServer) // Serve gRPC server log.Printf("server listening at %v", lis.Addr()) // Graceful shutdown sigCh := make(chan os.Signal, 1) signal.Notify(sigCh, os.Interrupt, syscall.SIGTERM) go func() { if err := s.Serve(lis); err != nil { log.Fatalf("failed to serve: %v", err) } }() <-sigCh log.Println("Shutting down gracefully...") s.GracefulStop() log.Println("Server stopped") } ``` **Penjelasan:** 1. **Import Packages:** Mengimpor paket-paket yang diperlukan, termasuk `mcp-go` dan paket-paket standar Go. 2. **`SimpleSource` struct:** Mengimplementasikan interface `Source` dari `mcp-go`. Interface ini mendefinisikan bagaimana server MCP mendapatkan dan menyediakan sumber daya. * `GetResources`: Mengembalikan daftar sumber daya untuk tipe tertentu. Dalam implementasi ini, sumber daya disimpan dalam `Resources` map. * `GenerateSnapshot`: Membuat snapshot dari sumber daya saat ini. Snapshot berisi versi dari setiap tipe sumber daya dan daftar sumber daya itu sendiri. * `Watch`: Memantau perubahan pada sumber daya dan mengirimkan event ke sink. Dalam contoh ini, hanya mengirimkan satu event dengan snapshot awal. Implementasi yang lebih kompleks akan memantau perubahan dan mengirimkan event delta. 3. **`main` function:** * **Listen:** Membuat listener TCP pada port yang ditentukan (18000). * **gRPC Server:** Membuat instance server gRPC. * **`SimpleSource` Instance:** Membuat instance `SimpleSource` dan mengisinya dengan beberapa sumber daya contoh. Sumber daya ini adalah `StringValue` dari `google.protobuf`. * **MCP Server:** Membuat instance server MCP menggunakan `server.New(source)`. * **Register Server:** Mendaftarkan server MCP dengan server gRPC menggunakan `mcp.RegisterAggregatedMeshConfigServiceServer(s, mcpServer)`. * **Serve:** Memulai server gRPC untuk melayani permintaan. * **Graceful Shutdown:** Menangani sinyal `SIGINT` dan `SIGTERM` untuk mematikan server secara anggun. **Cara menjalankan:** 1. **Pastikan Anda memiliki Go terinstal:** Unduh dan instal Go dari [https://go.dev/dl/](https://go.dev/dl/). 2. **Instal `mcp-go`:** ```bash go get istio.io/istio/pkg/mcp go get istio.io/api/mcp/v1alpha1 ``` 3. **Simpan kode:** Simpan kode di atas sebagai file `main.go`. 4. **Jalankan:** ```bash go run main.go ``` Server akan mulai berjalan di port 18000. **Cara menguji:** Anda dapat menggunakan alat seperti `grpcurl` untuk menguji server MCP. Berikut adalah contoh perintah untuk mengambil sumber daya: ```bash grpcurl -plaintext -d '{"type_url": "type.googleapis.com/google.protobuf.StringValue"}' localhost:18000 istio.mcp.v1alpha1.AggregatedMeshConfigService/StreamAggregatedResources ``` Perintah ini akan mengirimkan permintaan ke server MCP untuk sumber daya dengan tipe `type.googleapis.com/google.protobuf.StringValue`. Server akan merespons dengan daftar sumber daya yang dikonfigurasi dalam `SimpleSource`. **Catatan:** * Ini adalah implementasi minimal dan tidak menangani semua aspek server MCP yang lengkap. * Implementasi `Watch` hanya mengirimkan snapshot awal. Implementasi yang lebih kompleks akan memantau perubahan dan mengirimkan event delta. * Kode ini menggunakan sumber daya contoh. Anda perlu mengganti ini dengan sumber daya yang sesuai dengan kebutuhan Anda. * Anda perlu menginstal `grpcurl` untuk menguji server. Anda dapat menginstalnya menggunakan `go install github.com/fullstorydev/grpcurl/cmd/grpcurl@latest`. Kode ini memberikan dasar untuk membangun server MCP Golang menggunakan `mcp-go`. Anda dapat memperluasnya untuk mendukung lebih banyak tipe sumber daya, implementasi `Watch` yang lebih canggih, dan fitur-fitur lain yang diperlukan.

Apifox MCP Pro

Provides basic diagnostic and information tools for Apifox API management platform, including token validation, project access checks, and explanations of API limitations due to Apifox's restricted Open API.

Agent Communication MCP Server

Enables AI agents to communicate with each other through Slack-like room-based channels with messaging, mentions, presence management, and long-polling for real-time collaboration.

librarian

An MCP server that enables LLMs to search, summarize, and retrieve detailed information from Wikipedia across multiple languages. It supports automated fact-checking by allowing models to proactively verify factual claims using Wikipedia's database.

mcp-scholar

"mcp\_scholar" adalah alat berbasis Python untuk mencari dan menganalisis makalah Google Scholar, mendukung fitur-fitur seperti pencarian berbasis kata kunci dan integrasi dengan klien MCP dan Cherry Studio. Alat ini menyediakan fungsionalitas seperti mengambil makalah yang paling banyak dikutip dari profil scholar dan meringkas topik penelitian.

LINE Bot MCP Server

Server MCP yang mengintegrasikan LINE Messaging API untuk menghubungkan Agen AI ke Akun Resmi LINE.

CodeGraphContext

Indexes local Python code into a Neo4j graph database to provide AI assistants with deep code understanding and relationship analysis. Enables querying code structure, dependencies, and impact analysis through natural language interactions.

MCP Memory

A server that gives MCP clients (Cursor, Claude, Windsurf, etc.) the ability to remember user information across conversations using vector search technology.

Kubecost MCP Server

An implementation that enables AI assistants to interact with Kubecost cost management platform through natural language, providing access to budget management and cost analysis features.

Agentic Commerce MCP Demo

Enables interactive restaurant discovery and ordering through a synthetic commerce flow with rich HTML UI. Demonstrates agentic commerce UX with tools to find restaurants, view menus, place mock orders, and generate receipts.

Neva

SDK server MCP untuk Rust

Affilync MCP Server

Enables users to manage affiliate marketing directly within Claude by connecting to the Affilync platform. Affiliates can search campaigns and track earnings, while brands can create campaigns, monitor performance, and manage affiliate applications through natural language.

mcp-bauplan

Sebuah server MCP untuk berinteraksi dengan data dan menjalankan pipeline menggunakan Bauplan.

MCP-LinkedIn

Dynamic tools to automate tasks on LinkedIn website.

MCP Pi-hole Server

Connects AI assistants to Pi-hole network-wide ad blocker, enabling monitoring of DNS traffic statistics, controlling blocking settings, managing whitelist/blacklist domains, viewing query logs, and performing maintenance tasks through natural language.

Graphiti Knowledge Graph MCP Server

Enables AI assistants to build and query temporally-aware knowledge graphs from conversations and data. Supports adding episodes, searching entities and facts, and maintaining persistent memory across interactions.

Grasp

An open-source self-hosted browser agent that provides a dockerized browser environment for AI automation, allowing other AI apps and agents to perform human-like web browsing tasks through natural language instructions.

Remote MCP Server for Cloudflare

A deployable server that implements the Model Context Protocol (MCP) on Cloudflare Workers, enabling integration of custom tools with AI assistants like Claude without requiring authentication.

roslyn-codelens-mcp

Roslyn-based MCP server providing semantic code intelligence for .NET codebases — type hierarchies, call sites, DI registrations, and reflection usage for Claude Code