Discover Awesome MCP Servers

remote-mcp-server-authless

A remote MCP server deployable on Cloudflare Workers without authentication, allowing custom tool definitions and connections to MCP clients like Cloudflare AI Playground or Claude Desktop.

Wazuh MCP Server

Enables AI assistants to query Wazuh security alerts, investigate hosts, detect brute-force attempts, and generate security summaries by connecting to a Wazuh manager.

timeweb-mcp-server

Enables deploying applications and managing cloud resources in Timeweb Cloud through natural language.

Coordinalo MCP Server

Connects AI agents to Coordinalo's scheduling platform, enabling booking management, availability checks, client management, and reporting through MCP tools.

actionforge-mcp

Bridges ActionForge's hosted function endpoints to any MCP client, letting Claude and others call your generated tools directly.

Telegram MCP Server

A Model Context Protocol server that enables AI assistants to interact with Telegram, allowing them to search channels, list available channels, retrieve messages, and filter messages by regex patterns.

Witness

Provides evidence-oriented MCP service for cryptographically identified agents, bounded public contracts, privacy-preserving records, and append-only audit.

turva-mcp

Public read-only MCP server for turva.dev's agent-readiness audit, enabling AI agents to query service catalog, security evidence, and engagement principles via structured JSON.

Tableau MCP Server

Enables AI applications to integrate with Tableau through tools, resources, and prompts for querying data, exploring content, and retrieving visualizations from Tableau workbooks and datasources.

Bi-Temporal Knowledge Graph MCP Server

Gives AI agents persistent memory with bi-temporal tracking, automatically extracting entities from natural language and enabling time-travel queries to understand facts as they existed at any point in history.

SAP Security Notes MCP Server

Enables querying SAP Security Note metadata including Patch Day releases, CVSS scores, CVEs, affected components, and actively-exploited status via the Model Context Protocol.

astrodynamics-mcp

An MCP server that equips LLM clients with authoritative astrodynamics tools including TLE/SGP4 propagation, Lambert solving, ground-station access, time-scale and coordinate-frame conversions, and more.

mcp-tmux

Remote-first tmux co-pilot that lets LLMs operate inside real tmux sessions with SSH-aware discovery, deterministic window/pane control, and pull-based state snapshots for grounded terminal assistance.

Todoist MCP Server

A proof-of-concept MCP server that interacts with Todoist using OAuth-based authorization and is deployed on Cloudflare Workers.

Confluence MCP Server

A Model Context Protocol (MCP) server that provides Confluence search functionality for LexisNexis internal systems.

RavenEye

Enables AI intelligence gathering by scanning RSS feeds and GitHub for high-value opportunities, then generating actionable Markdown reports through an MCP-integrated multi-agent platform.

TeamAPI-MCP

Manages API documentation via Markdown files and exposes it as MCP tools for querying, searching, and updating interface specs, with an admin web UI and REST API.

mcp-audit

A frontend security dependency auditing tool that identifies vulnerabilities in local and remote repositories using the Model Context Protocol. It provides detailed audit information like CVSS scores and dependency chains, generating standardized markdown reports.

Neurosift Mcps

Here are some MCP (Multi-Compute Pipeline) server options for Neuroglancer/Neurosift, along with some considerations: **1. Google Cloud Platform (GCP) - Recommended for Scalability and Integration** * **Why it's good:** * **Scalability:** GCP is designed for handling large datasets and high traffic. You can easily scale your compute resources as needed. * **Integration:** Neurosift is often used with data stored in Google Cloud Storage (GCS). Using GCP for your MCP server simplifies data access and reduces latency. * **Managed Services:** GCP offers managed services like Google Kubernetes Engine (GKE) and Cloud Functions that can simplify deployment and management. * **Cost-Effective:** With proper configuration and autoscaling, GCP can be cost-effective, especially for variable workloads. * **How to set it up (General Outline):** 1. **Create a GCP Project:** If you don't already have one. 2. **Set up a Compute Instance (VM):** Choose a VM with sufficient CPU, memory, and disk space for your needs. Consider using a preemptible VM to save costs (but be aware that it can be terminated). Install the necessary software (Python, Neurosift dependencies, etc.). 3. **Containerization (Docker):** It's highly recommended to containerize your MCP server using Docker. This makes deployment and management much easier. Create a `Dockerfile` that defines your server's environment. 4. **Deployment Options:** * **Direct VM Deployment:** You can run the Docker container directly on the VM. Use `docker run` to start the container. * **Google Kubernetes Engine (GKE):** GKE is a managed Kubernetes service that allows you to deploy and manage your MCP server as a containerized application. This is a good option for more complex deployments or when you need to scale your server. * **Cloud Functions:** For very simple MCP tasks, you *might* be able to use Cloud Functions, but this is less common for Neurosift due to the resource limitations and execution time constraints. 5. **Configure Firewall Rules:** Allow traffic to your MCP server on the appropriate port (e.g., 8080). 6. **Set up a Domain Name (Optional):** If you want to access your MCP server using a custom domain name, you'll need to configure DNS records. 7. **Security:** Implement appropriate security measures, such as using HTTPS and restricting access to your server. * **Example Dockerfile (Simplified):** ```dockerfile FROM python:3.9-slim-buster WORKDIR /app # Install dependencies COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt # Copy your MCP server code COPY . . # Expose the port your server listens on EXPOSE 8080 # Command to run the server CMD ["python", "your_mcp_server.py"] ``` * **Example `requirements.txt`:** ``` neurosift numpy # Add any other dependencies your server needs ``` **2. Amazon Web Services (AWS)** * **Why it's good:** Similar to GCP, AWS offers excellent scalability, a wide range of services, and good integration with other AWS services. * **How to set it up:** The process is very similar to GCP, but you'll use AWS equivalents: * **EC2:** For virtual machines (similar to GCP Compute Engine). * **Elastic Container Service (ECS) or Elastic Kubernetes Service (EKS):** For container orchestration (similar to GKE). * **Lambda:** For serverless functions (similar to Cloud Functions, but less likely to be suitable for most Neurosift MCP servers). * **S3:** For object storage (similar to GCS). **3. Microsoft Azure** * **Why it's good:** Another major cloud provider with similar capabilities to GCP and AWS. * **How to set it up:** Again, the process is similar, using Azure equivalents: * **Virtual Machines:** For virtual machines. * **Azure Kubernetes Service (AKS):** For container orchestration. * **Azure Functions:** For serverless functions. * **Azure Blob Storage:** For object storage. **4. Your Own Server (On-Premise or Dedicated Server)** * **Why it might be good:** * **Control:** You have complete control over the hardware and software. * **Cost (Potentially):** If you already have the hardware, it might be cheaper in the short term. * **Why it might *not* be good:** * **Maintenance:** You're responsible for all maintenance, security updates, and troubleshooting. * **Scalability:** Scaling can be difficult and time-consuming. * **Reliability:** You need to ensure the server is reliable and has adequate backup and redundancy. * **How to set it up:** 1. **Install the Operating System:** Choose a Linux distribution (e.g., Ubuntu, Debian, CentOS). 2. **Install Dependencies:** Install Python, Neurosift dependencies, and any other required software. 3. **Configure the Server:** Set up firewall rules, configure networking, and secure the server. 4. **Deploy Your MCP Server:** Run your MCP server code. Consider using a process manager like `systemd` or `supervisor` to ensure the server restarts automatically if it crashes. **Key Considerations for Choosing an MCP Server:** * **Data Location:** Where is your data stored (e.g., GCS, S3, local storage)? Choose an MCP server that is close to your data to minimize latency. * **Workload:** How much compute power do you need? How variable is your workload? If your workload is highly variable, a cloud-based solution with autoscaling is a good choice. * **Cost:** Compare the costs of different options, including compute, storage, and networking. Consider using preemptible VMs or spot instances to save costs. * **Complexity:** How comfortable are you with managing servers and infrastructure? A managed service like GKE or ECS can simplify deployment and management. * **Security:** Implement appropriate security measures to protect your data and server. **Important Notes:** * **Neurosift Documentation:** Refer to the official Neurosift documentation for the most up-to-date information and best practices. The documentation may have specific recommendations for MCP server setup. * **MCP Server Code:** You'll need to write the code for your MCP server. This code will handle requests from Neurosift and perform the necessary computations. The complexity of this code will depend on the specific tasks you need to perform. * **Example Code:** Look for example MCP server code in the Neurosift documentation or online. This can provide a starting point for your own server. * **Testing:** Thoroughly test your MCP server to ensure it is working correctly and can handle the expected load. **Translation to Indonesian:** Berikut adalah beberapa opsi server MCP (Multi-Compute Pipeline) untuk Neuroglancer/Neurosift, beserta beberapa pertimbangan: **1. Google Cloud Platform (GCP) - Direkomendasikan untuk Skalabilitas dan Integrasi** * **Mengapa bagus:** * **Skalabilitas:** GCP dirancang untuk menangani dataset besar dan lalu lintas tinggi. Anda dapat dengan mudah menskalakan sumber daya komputasi Anda sesuai kebutuhan. * **Integrasi:** Neurosift sering digunakan dengan data yang disimpan di Google Cloud Storage (GCS). Menggunakan GCP untuk server MCP Anda menyederhanakan akses data dan mengurangi latensi. * **Layanan Terkelola:** GCP menawarkan layanan terkelola seperti Google Kubernetes Engine (GKE) dan Cloud Functions yang dapat menyederhanakan penyebaran dan pengelolaan. * **Hemat Biaya:** Dengan konfigurasi dan penskalaan otomatis yang tepat, GCP bisa hemat biaya, terutama untuk beban kerja yang bervariasi. * **Cara menyiapkan (Garis Besar Umum):** 1. **Buat Proyek GCP:** Jika Anda belum memilikinya. 2. **Siapkan Instance Komputasi (VM):** Pilih VM dengan CPU, memori, dan ruang disk yang cukup untuk kebutuhan Anda. Pertimbangkan untuk menggunakan VM preemptible untuk menghemat biaya (tetapi ketahui bahwa VM tersebut dapat dihentikan). Instal perangkat lunak yang diperlukan (Python, dependensi Neurosift, dll.). 3. **Kontainerisasi (Docker):** Sangat disarankan untuk mengontainerisasi server MCP Anda menggunakan Docker. Ini membuat penyebaran dan pengelolaan jauh lebih mudah. Buat `Dockerfile` yang mendefinisikan lingkungan server Anda. 4. **Opsi Penyebaran:** * **Penyebaran VM Langsung:** Anda dapat menjalankan kontainer Docker langsung di VM. Gunakan `docker run` untuk memulai kontainer. * **Google Kubernetes Engine (GKE):** GKE adalah layanan Kubernetes terkelola yang memungkinkan Anda menyebarkan dan mengelola server MCP Anda sebagai aplikasi yang dikontainerisasi. Ini adalah pilihan yang baik untuk penyebaran yang lebih kompleks atau ketika Anda perlu menskalakan server Anda. * **Cloud Functions:** Untuk tugas MCP yang sangat sederhana, Anda *mungkin* dapat menggunakan Cloud Functions, tetapi ini kurang umum untuk Neurosift karena keterbatasan sumber daya dan batasan waktu eksekusi. 5. **Konfigurasikan Aturan Firewall:** Izinkan lalu lintas ke server MCP Anda pada port yang sesuai (misalnya, 8080). 6. **Siapkan Nama Domain (Opsional):** Jika Anda ingin mengakses server MCP Anda menggunakan nama domain khusus, Anda perlu mengonfigurasi catatan DNS. 7. **Keamanan:** Terapkan langkah-langkah keamanan yang sesuai, seperti menggunakan HTTPS dan membatasi akses ke server Anda. * **Contoh Dockerfile (Disederhanakan):** ```dockerfile FROM python:3.9-slim-buster WORKDIR /app # Instal dependensi COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt # Salin kode server MCP Anda COPY . . # Ekspos port tempat server Anda mendengarkan EXPOSE 8080 # Perintah untuk menjalankan server CMD ["python", "your_mcp_server.py"] ``` * **Contoh `requirements.txt`:** ``` neurosift numpy # Tambahkan dependensi lain yang dibutuhkan server Anda ``` **2. Amazon Web Services (AWS)** * **Mengapa bagus:** Mirip dengan GCP, AWS menawarkan skalabilitas yang sangat baik, berbagai layanan, dan integrasi yang baik dengan layanan AWS lainnya. * **Cara menyiapkan:** Prosesnya sangat mirip dengan GCP, tetapi Anda akan menggunakan padanan AWS: * **EC2:** Untuk mesin virtual (mirip dengan GCP Compute Engine). * **Elastic Container Service (ECS) atau Elastic Kubernetes Service (EKS):** Untuk orkestrasi kontainer (mirip dengan GKE). * **Lambda:** Untuk fungsi tanpa server (mirip dengan Cloud Functions, tetapi kurang mungkin cocok untuk sebagian besar server MCP Neurosift). * **S3:** Untuk penyimpanan objek (mirip dengan GCS). **3. Microsoft Azure** * **Mengapa bagus:** Penyedia cloud utama lainnya dengan kemampuan serupa dengan GCP dan AWS. * **Cara menyiapkan:** Sekali lagi, prosesnya serupa, menggunakan padanan Azure: * **Virtual Machines:** Untuk mesin virtual. * **Azure Kubernetes Service (AKS):** Untuk orkestrasi kontainer. * **Azure Functions:** Untuk fungsi tanpa server. * **Azure Blob Storage:** Untuk penyimpanan objek. **4. Server Anda Sendiri (On-Premise atau Server Dedicated)** * **Mengapa mungkin bagus:** * **Kontrol:** Anda memiliki kontrol penuh atas perangkat keras dan perangkat lunak. * **Biaya (Potensial):** Jika Anda sudah memiliki perangkat keras, mungkin lebih murah dalam jangka pendek. * **Mengapa mungkin *tidak* bagus:** * **Pemeliharaan:** Anda bertanggung jawab atas semua pemeliharaan, pembaruan keamanan, dan pemecahan masalah. * **Skalabilitas:** Penskalaan bisa sulit dan memakan waktu. * **Keandalan:** Anda perlu memastikan server andal dan memiliki cadangan dan redundansi yang memadai. * **Cara menyiapkan:** 1. **Instal Sistem Operasi:** Pilih distribusi Linux (misalnya, Ubuntu, Debian, CentOS). 2. **Instal Dependensi:** Instal Python, dependensi Neurosift, dan perangkat lunak lain yang diperlukan. 3. **Konfigurasikan Server:** Siapkan aturan firewall, konfigurasikan jaringan, dan amankan server. 4. **Sebarkan Server MCP Anda:** Jalankan kode server MCP Anda. Pertimbangkan untuk menggunakan pengelola proses seperti `systemd` atau `supervisor` untuk memastikan server dimulai ulang secara otomatis jika terjadi crash. **Pertimbangan Utama untuk Memilih Server MCP:** * **Lokasi Data:** Di mana data Anda disimpan (misalnya, GCS, S3, penyimpanan lokal)? Pilih server MCP yang dekat dengan data Anda untuk meminimalkan latensi. * **Beban Kerja:** Berapa banyak daya komputasi yang Anda butuhkan? Seberapa bervariasi beban kerja Anda? Jika beban kerja Anda sangat bervariasi, solusi berbasis cloud dengan penskalaan otomatis adalah pilihan yang baik. * **Biaya:** Bandingkan biaya opsi yang berbeda, termasuk komputasi, penyimpanan, dan jaringan. Pertimbangkan untuk menggunakan VM preemptible atau instance spot untuk menghemat biaya. * **Kompleksitas:** Seberapa nyaman Anda mengelola server dan infrastruktur? Layanan terkelola seperti GKE atau ECS dapat menyederhanakan penyebaran dan pengelolaan. * **Keamanan:** Terapkan langkah-langkah keamanan yang sesuai untuk melindungi data dan server Anda. **Catatan Penting:** * **Dokumentasi Neurosift:** Lihat dokumentasi Neurosift resmi untuk informasi terbaru dan praktik terbaik. Dokumentasi mungkin memiliki rekomendasi khusus untuk pengaturan server MCP. * **Kode Server MCP:** Anda perlu menulis kode untuk server MCP Anda. Kode ini akan menangani permintaan dari Neurosift dan melakukan perhitungan yang diperlukan. Kompleksitas kode ini akan bergantung pada tugas spesifik yang perlu Anda lakukan. * **Contoh Kode:** Cari contoh kode server MCP dalam dokumentasi Neurosift atau online. Ini dapat memberikan titik awal untuk server Anda sendiri. * **Pengujian:** Uji secara menyeluruh server MCP Anda untuk memastikan server berfungsi dengan benar dan dapat menangani beban yang diharapkan.

GCP Diagram MCP Server

Generates GCP architecture diagrams, sequence diagrams, flow charts, and class diagrams using Python diagrams DSL via MCP.

molt-mcp

Provides LLMs with access to molt-md, an encrypted markdown document hosting service, for managing and reading secure knowledge bases. It enables users to create, update, and organize encrypted documents into workspaces with full version control and end-to-end encryption.

MCP Cron Server

A standalone scheduling service providing cron-like job capabilities through the Model Context Protocol. It allows users to manage and execute scheduled tasks in OpenCode using natural language commands.

sofa-mcp

Enables MCP clients to search, read, and interact with Stack Overflow for Agents posts and Stack Exchange Q&A, including posting, replying, voting, verification, and session management through 17 stdio tools.

governance-mcp-server

MCP server for querying the DodaOne governance framework, enabling users to retrieve governance information and evaluate proposed actions.

OpenAPI MCP Server

Ini adalah proyek kerangka yang dapat Anda gunakan sebagai titik awal untuk membangun server MCP Anda sendiri. Fungsi penambahan contoh menunjukkan cara mengimplementasikan handler di ketiga protokol.

MCP Pytest Server

An MCP-compliant server that enables the execution of pytest test suites and the storage of results into a QA platform database. It allows AI models to trigger test runs, track execution progress, and retrieve historical test data through specialized tool interfaces.

Just-Magic MCP Server

Enables SEO automation through the Just-Magic.org API, including semantic clustering, LSI analysis, Wordstat frequency collection, text analysis, and task management.

ReforgerForge MCP

Enables AI-powered modding for Arma Reforger with 50 tools for API search, code generation, project scaffolding, and Workbench control.

Workflow Orchestration MCP Server

Guides AI agents through structured, multi-step workflows with discovery, navigation, and fidelity enforcement.