Cloud Platforms MCP servers

Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the [Streamable HTTP transport](https://modelcontextprotocol.io/specification/2025-03-26/basic/transportsstreamable-http) and builds on Metabase's Agent API to expose tools for searching, navigating, querying, visualizing, and creating/updating content - all scoped to the connecting user's permissions. The legacy /api/mcp path still works as an alias for existing clients, but /api/metabase-mcp is the canonical URL to advertise.

6 tools · construct_query, create_dashboard

MCP server for accessing Amazon Bedrock Knowledge Bases - Find and explore all available knowledge bases - Search for knowledge bases by name or tag - List data sources associated with each knowledge base - Retrieve information using conversational queries - Get relevant passages from your knowledge bases - Access citation information for all results - Focus your queries on specific data sources - Include or exclude specific data sources - Prioritize results from specific data sources - Improve relevance of retrieval results - Use Amazon Bedrock reranking capabilities - Sort results by relevance to your query

4 tools · Filter results by data source, list_knowledge_bases

Analyze CDK projects to identify AWS services used and get pricing information from AWS pricing webpages and API.

Core AWS MCP server providing prompt understanding and server management capabilities.

This AWS Labs Model Context Protocol (MCP) server for CloudTrail enables your AI agents to query AWS account activity for security investigations, compliance auditing, and operational troubleshooting. It provides comprehensive access to CloudTrail events and CloudTrail Lake analytics, allowing agents to track API calls, analyze user activity, and perform advanced security analysis. This server gives AI agents seamless access to CloudTrail data through standardized MCP interfaces, eliminating the need for custom API integrations and enabling powerful security insights and audit capabilities.

4 tools · get_query_status, lake_query

Get prescriptive CDK advice, explain CDK Nag rules, check suppressions, generate Bedrock Agent schemas, and discover AWS Solutions Constructs patterns.

This repo is the one-stop shop for building AI-powered products and businesses on top of Stripe. It contains a collection of SDKs to help you integrate Stripe with LLMs and agent frameworks, including: @stripe/ai-sdk - for integrating Stripe's billing infrastructure with Vercel's ai and @ai-sdk libraries. @stripe/token-meter - for integrating Stripe's billing infrastructure with native SDKs from OpenAI, Anthropic, and Google Gemini, without any framework dependencies. Stripe hosts a remote MCP server at https://mcp.stripe.com. This allows secure MCP client access via OAuth. View the docs here.

6 tools · Add Stripe plugin to Codex, Build autonomous agents

> 💡 Recommended: MiniMax CLI (mmx-cli) — our official command-line tool with the latest models and additional features including text, vision, and search. Works as an AI agent skill for Claude Code, Cursor, OpenClaw, etc. - 中文文档 - MiniMax-MCP-JS - Official JavaScript implementation of MiniMax MCP 1. Get your API key from MiniMax. 2. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods. 3. Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.

6 tools · generate_video, list_voices

The gcloud Model Context Protocol (MCP) server enables AI assistants to easily interact with the Google Cloud environment using the gcloud CLI. With the gcloud MCP server you can: - Interact with Google Cloud using natural language. Describe the outcome you want instead of memorizing complex command syntax, flags, and arguments. - Automate and simplify complex workflows. Chain multiple cloud operations into a single, repeatable command to reduce manual effort and the chance of error. - Lower the barrier to entry for cloud management. Empower team members who are less familiar with gcloud to perform powerful actions confidently and safely.

5 tools · execute_insights_query, gcloud

Enable MCP-compatible AI agents to deploy apps to Cloud Run. Deploy from Gemini CLI and other AI-powered CLI agents: Deploy from agent SDKs, like the Google Gen AI SDK or Agent Development Kit. > [!NOTE] > This is the repository of an MCP server to deploy code to Cloud Run, to learn how to host MCP servers on Cloud Run, visit the Cloud Run documentation. - deploy-file-contents: Deploys files to Cloud Run by providing their contents directly. - list-services: Lists Cloud Run services in a given project and region. - get-service: Gets details for a specific Cloud Run service. - get-service-log: Gets Logs and Error Messages for a specific Cloud Run service.

5 tools · deploy, Deploy code directly to Cloud Run

The PayPal Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with PayPal APIs through function calling. It includes support for TypeScript and is built on top of PayPal APIs and the PayPal SDKs. The PayPal Agent toolkit provides the following tools: - create_invoice: Create a new invoice in the PayPal system, including recipient billing details, line items, an invoice note, a custom color theme, an optional shipping cost, and an option to enable PAY_BY_BANK as a payment method - list_invoices: List invoices with optional pagination and filtering - get_invoice: Retrieve details of a specific invoice - send_invoice: Send an invoice to recipients - send_invoice_reminder: Send a reminder for an existing invoice - cancel_sent_invoice: Cancel a sent invoice - generate_invoice_qr_code: Generate a QR code for an invoice - delete_invoice: Permanently delete a draft or scheduled invoice - generat

6 tools · create_invoice, create_order

AlibabaCloud Devops MCP Server provides AI assistants with the ability to interact with the Yunxiao platform, enabling them to read work item contents in projects, automatically write code after understanding requirements, and submit code merge requests. Enterprise development teams can use it to assist with code reviews, optimize task management, reduce repetitive operations, and thus focus on more important innovation and product delivery. alibabacloud-devops-mcp-server provides the following capabilities for AI assistants:

6 tools · execute_app_release_stage, get_organization_departments

A Node.js server implementing Model Context Protocol (MCP) for Webflow using the Webflow JavaScript SDK. Enable AI agents to interact with Webflow APIs. Learn more about Webflow's Data API in the developer documentation. Get started by installing Webflow's remote MCP server. The remote server uses OAuth to authenticate with your Webflow sites, and a companion app that syncs your live canvas with your AI agent. > Note: The MCP server currently supports Node.js 22.3.0 or higher. If you run into version issues, see the Node.js compatibility guidance.

4 tools · Add internal links across blog posts, Analyze CMS content and suggest new topics

> [!IMPORTANT] > Private Preview Notice > The Gemini Cloud Assist MCP server APIs are currently in Private Preview and are behind an allowlist. Please contact your Google Cloud account team to request access. > [!WARNING] > Deprecation Notice & Migration to Remote MCP Server > > The Gemini Cloud Assist MCP server has migrated from a local Node.js architecture to a Remote MCP Server architecture. The older local Node.js server will lose support in the coming months. > > To use the new Remote MCP Servers, please use version v0.8.0 or later. If you wish to continue using the legacy local server during the transition, please pin your configuration to older versions.

6 tools · ask_cloud_assist, design_infra

Official Model Context Protocol (MCP) server for esa.io - STDIO transport version. This MCP server provides seamless integration between AI assistants and esa.io, a collaborative documentation platform. It enables AI assistants to read, create, update, and manage esa documents directly through the Model Context Protocol. - esa_get_teams - Get user's accessible esa teams - esa_get_team_stats - Get team statistics (members, posts, comments, stars, watches, active users) - esa_get_team_tags - Get all tags used in team posts with count - esa_get_team_members - Get team members with roles and profile information

6 tools · esa_archive_post, esa_create_post

This repository is deprecated and no longer maintained. Please use the official Axiom MCP Server at https://mcp.axiom.co instead. A Model Context Protocol server implementation for Axiom that enables AI agents to query your data using Axiom Processing Language (APL). Works with Claude desktop app. Implements six MCP tools: - queryApl: Execute APL queries against Axiom datasets - listDatasets: List available Axiom datasets - getDatasetSchema: Get dataset schema - getSavedQueries: Retrieve saved/starred APL queries - getMonitors: List monitoring configurations - getMonitorsHistory: Get monitor execution history

5 tools · Access saved APL queries, Check monitor status and history

Netlify MCP Server follows the Model Context Protocol (MCP) to enable code agents to use the Netlify API and CLI—so they can create new projects, build, deploy, and manage your Netlify resources using natural language prompts. The Model Context Protocol is an emerging standard protocol for connecting code agents with MCP servers, allowing them to manage resources and perform tasks using natural language. The Netlify MCP Server acts as a bridge, providing API access, CLI tools, prompts, and more for your agents.

6 tools · Configure environment variables, Create and deploy projects

Want a ready-to-use AI experience for DataWorks without manual MCP setup? DataWorks Agent is Alibaba Cloud's built-in intelligent assistant for data development and operations. It connects to your DataWorks workspace out of the box, so you can use natural language to explore metadata, develop nodes, troubleshoot tasks, and manage resources—no local MCP server configuration required. 👉 Get started: https://dataworks.data.alibabacloud.com/product/agent?source=github A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the DataWorks Open API through a standardized interface. This implementation is based on the Aliyun Open API and enables AI agents to perform cloud resources operations seamlessly.

4 tools · Explore workspace metadata, Filter available tools by category or name

- MCP Server for IBM Instana - 📚 Quick Links - Architecture Overview - Workflow - Prerequisites - Option 1: Install from PyPI (Recommended) - Option 2: Development Installation - Installing uv - Setting Up the Environment - Header-Based Authentication for Streamable HTTP Mode - 1. API Token Authentication (Direct API Calls) - 2. Session Token Authentication (UI-Initiated Calls) - 3. JWT Token Authentication (IBM Platform Integration) - Starting the Local MCP Server - Server Command Options - Using the CLI (PyPI Installation) - Using Development Installation - Starting in Streamable HTTP Mode - Using CLI (PyPI Installation) - Using Development Installation - Starting in Stdio Mode - Using CLI (PyPI Installation) - Using Development Installation - Tool Categories - Using CLI (PyPI Installation) - Using Development Installation - SSL Certificate Verification - Using the CLI option - Using the environment variable - Using a custom CA bundle - Verifying Server Status - Common Startup Issues

5 tools · app, events

The Globus MCP Server enables LLM applications to interact with Globus services. - globus_transfer_list_endpoints_and_collections - List endpoints and collections the user has access to - globus_transfer_search_endpoints_and_collections - Use a filter string to search all endpoints and collections that are visible to the user - globus_transfer_submit_task - Submit a transfer task between two collections - globus_transfer_get_task_events - Get a list of task events - globus_transfer_list_directory - List contents of a directory on a collection

6 tools · globus_compute_get_task_status, globus_compute_register_python_function

Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. This repository provides comprehensive MCP servers for Cloudinary's media management platform, enabling you to use natural language to upload, transform, analyze, and organize your media assets directly from AI applications like Cursor and Claude. With these MCP servers, you can seamlessly manage your entire media workflow through conversational AI - from uploading and transforming images and videos, to configuring automated processing pipelines, analyzing content with AI-powered tools, and organizing assets with structured metadata. Whether you're building media-rich applications, managing large asset libraries, or automating content workflows, these servers provide direct access to Cloudinary's full suite of media optimization and management capabilities.

6 tools · Build workflow automations, Configure environment settings

Run containerized workloads across AWS, GCP, Azure, OCI, and your own hardware under one API. It loads Control Plane's domain knowledge, production guardrails, and live MCP tools into Claude Code, Codex, and Antigravity CLI so your assistant can deploy, troubleshoot, secure, and migrate workloads with verified cpln commands. Update with /plugin marketplace update controlplane then /reload-plugins (third-party marketplaces don't auto-update unless you enable it in /plugin → Marketplaces). Alternatively, install from Anthropic's community plugin marketplace, where every listing has passed Anthropic's review:

5 tools · Configure networking and TLS, Deploy a workload from Kubernetes manifests

[![NPM Version][npm-shield]][npm-url] [![Contributors][contributors-shield]][contributors-url] [![Forks][forks-shield]][forks-url] [![Stargazers][stars-shield]][stars-url] [![Issues][issues-shield]][issues-url] [![MIT License][license-shield]][license-url] [![Discord][discord-shield]][discord-url] > Transform your content operations with AI-powered tools for Kontent.ai. Create, manage, and explore your structured content through natural language conversations in your favorite AI-enabled editor. Kontent.ai MCP Server implements the Model Context Protocol to connect your Kontent.ai projects with AI tools like Claude, Cursor, and VS Code. It enables AI models to understand your content structure and perform operations through natural language instructions.

5 tools · Administer environment settings, Control publishing and workflows

Mezmo MCP is a remote Model Context Protocol (MCP) server that lets AI assistants and IDE chat agents interact with the Mezmo observability platform via the Model Context Protocol. Use it for streamlined observability, log analysis, and root-cause analysis in your favorite tools. - 🕵️ Run advanced Root-cause analysis over recent logs - 📦 List and describe Pipelines - 📤 Export and filter Logs with powerful query syntax Mezmo MCP is a remote MCP server that connects AI assistants and IDE chat to Mezmo so you can run advanced root-cause analysis, discover pipelines, and export logs without hosting anything yourself. It's built for observability use cases and works across many popular MCP clients.

3 tools · export_logs, list_pipelines

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat. You will need a Rostro account for OAuth discovery and authentication in your client of choice. MCP Server URL: https://proto.rostro.dev/mcp - Cursor: Install in Cursor - LM Studio: Install in LM Studio For fixed API authentication instead of OAuth, add this to your settings:

3 tools · generate_image, generate_music

Publish the website you built with AI to a live public URL — straight from chat, no setup. Describe a site to your AI assistant — ChatGPT, Claude, Gemini, or any MCP-enabled client — and it publishes the site and hands back a live URL. No git, no CLI, no build step, no dashboard, and no login to fumble through. You hand it your files, it hands back a working link. Built for the person who made a site with AI and just wants it online. - Website: https://justpublish.ai - MCP endpoint: https://mcp.justpublish.ai/ - Registry name: ai.justpublish/just-publish - Transport: Streamable HTTP (remote — nothing to install)

4 tools · deploy, get_site_files

Databox MCP is a Model Context Protocol server that connects your business data to AI assistants. Ask questions about your metrics in plain English—no SQL, no dashboard building, no data exports. Databox MCP enables AI tools like Claude, Cursor, n8n, and Gemini CLI to access and analyze your Databox data conversationally. It transforms how you interact with business metrics—instead of navigating dashboards, you simply ask questions and get instant answers. Key Benefits: - Query your data using natural language - Works with 130+ existing Databox integrations - No additional cost for Databox users - Setup in under 60 seconds

6 tools · ask_genie, create_data_source

> These are the tools exposed by the StackQL MCP server. Availability of mutation and lifecycle tools depends on the server mode (read_only, safe, delete_safe, full_access). Providers pulled into the local StackQL cache Resources available under a provider.service

4 tools · describe_method, describe_resource

The official Terraform MCP Server seamlessly integrates with the Terraform ecosystem, enabling provider discovery, module analysis, and direct Registry API integration for advanced Infrastructure as Code workflows.

5 tools · Access private registry content, List organizations and projects

Vulnebify is a cyber defense software that monitors and notifies on vulnerabilities in real time, protecting companies and countries from emerging threats.

MCP Server https://mcp.websitepublisher.ai Auth OAuth 2.1 (auto-discovery) or Bearer token Three ways to connect. Option A is the quickest — WebsitePublisher is listed in Anthropic's Connectors Directory, so it takes one click and works on every Claude plan, free included. Option B configures Claude Desktop for you and also sets up Cursor, Windsurf and VS Code. Option C is manual MCP config. Go straight to the WebsitePublisher listing, or in claude.ai open Settings → Connectors and search for WebsitePublisher. Nothing to paste, nothing to configure.

4 tools · create_entity, create_page

Build and host full-stack web apps and sites on Hatchable from any MCP client. DB, auth, storage, domains, and cron per project. Free tier.

Full Easypanel control from Claude Code and Cursor — 37 tools for deployments, services, env vars, logs, domains, databases and monitoring. Safety guards require explicit confirmation for all destructive actions.

Manage Proxmox VE clusters through AI assistants — VMs, containers, snapshots, templates, cloud-init, firewall, and migrations. 29 tools with two-step confirmation for destructive operations.

Provides MCP multi-cluster Kubernetes management and operations. It can be integrated as an SDK into your own project and includes nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources.

A MCP server for LocalStack to manage local AWS environments, including lifecycle operations, infra deployments, log analysis, fault injection, and state management.

Compute price oracle for AI agents. Compare inference pricing across 8 providers in real time with routing recommendations and spend tracking. One-command install: `npx volthq-mcp-server --setup`.

A Terraform MCP server allowing AI assistants to manage and operate Terraform environments, enabling reading configurations, analyzing plans, applying configurations, and managing Terraform state.

Microsoft Graph MCP server — 85 tools across Outlook mail & calendar, Teams, OneDrive, SharePoint, OneNote, Planner and Entra ID. Delegated OAuth, stdio or Streamable HTTP.

mcp server for [cert-manager](https://github.com/cert-manager/cert-manager) management and troubleshooting

Read-only `kubectl` for Claude Code: returns structured JSON, hardcoded safe verbs (no mutation path even with malicious input), Secret/ConfigMap values never returned, plus one-shot cluster triage & inventory.

VMware vSphere storage management — datastores (NFS/VMFS), iSCSI software adapter and dynamic targets, and vSAN cluster operations. 11 tools with dry-run preview and double-confirmation for iSCSI configuration changes.

Adobe Edge Delivery Services (AEM EDS) management with 20 tools for preview, publish, bulk operations, content reading, Core Web Vitals, 404 tracking, A/B experiments, site configuration, and redirects. Install: `npx @focusgts/eds-mcp-server`.

Manage Cloudflare Workers, KV, R2, Pages, DNS, and cache from your IDE.

One MCP server holding a live session with every client's account at once, so one agent can read across a dozen businesses and write inside only the one you name. Forwards each provider's own MCP tools (Cloudflare, Vercel, Resend, Supabase, Linear, Notion, Sentry, Netlify, Zoho and more) with that client's credentials, plus deterministic DNS and email checks that never call a model. Install: `uv tool install munim`.

VMware AVI Load Balancer (NSX ALB) management plus AKO Kubernetes integration. 29 tools across virtual services, pools, analytics metrics, and AKO lifecycle (restart/upgrade/force-resync) with double-confirmation for destructive ops.

Get up-to-date EC2 pricing information with one call. Fast. Powered by a pre-parsed AWS pricing catalogue.

AI-powered SRE observability for Kubernetes and OpenShift with 40+ tools for Tekton pipeline debugging, log analysis, root cause analysis, and predictive monitoring.

Manages one or more Docker daemons (local socket or remote over TCP/TLS/SSH) with 156 tools spanning containers, images, Compose, Swarm, Buildx, Scout, and OCI registries. Mark hosts as read-only for safe monitoring; logs and stats exposed as MCP resources.

VMware vSphere/vCenter management — VM lifecycle (create/clone/delete/migrate), deployment, Guest Operations, snapshots, and cluster operations. 41 tools with double-confirmation gates, dry-run mode, and SQLite-WAL audit logging for destructive operations.

An MCP server that allows AI agents to manage Kubernetes resources through Cyclops abstraction

Inspect and manage IONOS CLOUD infrastructure via MCP.

Deploy live HTTPS websites in seconds. Instant subdomains ($1 USDC) or custom .xyz domains ($10 USDC) on Base chain. Templates for crypto tokens and AI agent profiles.

MCP server for the Dynadot domain registrar API — 60 tools for domain search, registration, DNS, contacts, transfers, and marketplace.

All four Proxmox surfaces — VE, Backup Server, Mail Gateway, Datacenter Manager — plus in-container exec on one audited control plane. Every mutation dry-runs to a PLAN with its blast radius named, snapshots first where the platform can, and lands in a hash-chained tamper-evident audit ledger. 365 tools, read-only by default. `uvx proximo-proxmox`

A Model Context Protocol server for querying and analyzing Azure resources at scale using Azure Resource Graph, enabling AI assistants to explore and monitor Azure infrastructure.

Publish HTML an agent makes to a private, unguessable URL. Every link is private by default; gate one with a passcode or a company-email domain that viewers pass without creating an account, set an expiry or burn-after-read, and replace it in place so the shared URL always shows the current version. Paid plans add read analytics on who opened the page. OAuth with dynamic client registration, or a stdio package.

Administer a self-hosted [wg-easy](https://github.com/wg-easy/wg-easy) (WireGuard Easy) v15 instance: list, create, update, enable/disable and delete VPN clients, fetch configuration files and QR codes, generate one-time links, and inspect server status. Deleting a client takes a two-step, server-issued confirmation token; admin secrets are redacted from responses. `npx -y wg-easy-mcp`

MKP is a Model Context Protocol (MCP) server for Kubernetes that allows LLM-powered applications to interact with Kubernetes clusters. It provides tools for listing and applying Kubernetes resources through the MCP protocol.

Governed Nutanix Prism Central v4 operations — cluster, VM (AHV + ESXi), storage, networking, snapshot/DR, alerts, and LCM (51 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

Self-hosted MCP server suite for Odoo ERP (versions 15-19). 197+ tools across 8 federated MCP servers (odoo-rpc, GitHub, Portainer, OCA, Teams, filesystem). Multi-tenant Claude/Claude Code integration, browser-based xterm.js + tmux terminal, Qdrant + Ollama memory layer, Bulgaria localization (НАП, ДДС, ЕИК). Docker Compose + K3s/Kustomize deployment.

Kubernetes bulk port forwarding with service discovery, /etc/hosts management, traffic monitoring, and pod log streaming

Unified deployment dashboard MCP server across Vercel, Render, Railway, and Fly.io. 9 tools for deploy status, logs, environment variables, rollback, and health checks across all platforms. Free tier with x402 micropayments.

A wrapper around the Azure CLI command line that allows you to talk directly to Azure

OpenStack MCP server for cloud infrastructure management based on openstacksdk.

MCP Server for Kubernetes integrated with Open-WebUI, bridging the gap between DevOps and non-technical teams. Supports `kubectl` and `helm` operations through natural-language commands.

Safety-first Terraform operations: plan/apply/destroy with two-step confirmation gates, plan risk & cost analysis that flags expensive always-on resources (NAT gateways, EKS, Azure Firewall), drift detection, import/taint/refresh, provider auth pre-flight checks, and audit logging.

Natural-language cloud architecture intelligence for AWS, GCP, Azure, and Databricks. 19 tools for architecture design, cost estimation, compliance validation (HIPAA, SOC 2, FedRAMP, GDPR, PCI-DSS, Well-Architected), security scanning, Terraform/CloudFormation export, and blast-radius analysis.

A lightweight but powerful server that enables AI assistants to execute AWS CLI commands, use Unix pipes, and apply prompt templates for common AWS tasks in a safe Docker environment with multi-architecture support

Provision, SSH into, run commands on, and manage Linux VPSes from an agent — pay USDC over x402 or by card over HTTP 402, a running box in under 60s. No signup, no API key to buy.

Implementation of MCP server for [Kestra](https://kestra.io) workflow orchestration platform.

Open source podcast hosting platform

Lizard, the AI-native deployment platform for coding agents: ship services, add managed Postgres, Redis and S3, stream logs and metrics, set secrets, scale and attach domains. 33 tools, OAuth 2.1, destructive actions require confirmation.

Agent-native hosting: deploy any app to a live URL in one command — no account, no dashboard, no CAPTCHA. Full deploy lifecycle as tools (deploy, verify, logs, inspect, rollback, list/delete); production approval stays human-only. Apache-2.0.

Unofficial agentic MCP server for Infomaniak (Swiss cloud provider). 54 tools covering web hosting, mail, kDrive, domains, DNS, DNSSEC, FTP/SSH users, AI catalogue and more. Two-phase commit on every destructive operation, history & undo, transparent reverse-engineering of undocumented manager-private endpoints.

AWS S3 operations — list buckets, browse objects, upload/download files, and generate presigned URLs.

Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents. Streamable HTTP at `https://api.novence.ai/mcp`.

Publish what an agent just wrote to a live HTTPS URL. Three tools: `publish_files` for pages written in the chat, `publish_dir` for a folder on disk, and `list_sites`. Static hosting on Cloudflare's edge, so no git, no build step and no repository. `npx -y @drop2run/mcp`

MCP server implementation for PythonAnywhere cloud platform.

Typescript implementation of Kubernetes cluster operations for pods, deployments, services.

Docker container management for AI agents — health checks, auto-restart, Compose lifecycle, and log streaming. 50+ tools for the agent operations loop.

Official Adios MCP server for managing workspaces, previews, builds, logs, services, and production deployments.

MCP server for Kubernetes cluster operations — inspect pods, deployments, services, and logs via AI agents.

Azure cloud cost management — spending analysis, forecasts, anomaly detection, budgets, optimization recommendations, idle resource detection, tag-based cost allocation, and cross-subscription queries through natural language.

Code Mode MCP server for the entire OVH API. Two tools (search + execute) give LLMs access to all OVH endpoints via sandboxed JavaScript, using ~1,000 tokens instead of thousands of tool definitions.

upload and manipulation of IPFS storage

Official Espressif MCP Server to manage and control ESP RainMaker Devices.

Manage MikroTik RouterOS devices through AI assistants — interfaces, firewall rules, DHCP, DNS, routes, WireGuard, WiFi, BGP/OSPF, VLANs, and more. 77 tools with dry-run previews, idempotency checks, circuit breakers, RBAC, and rollback-aware change workflows.

MCP Server for kubernetes management, and analyze your cluster, application health

Oracle Cloud Infrastructure pricing data with 602 products, cost calculators, and cross-provider comparisons. One-command install for Claude.

MCP server for interacting with Pulumi using the Pulumi Automation API and Pulumi Cloud API. Enables MCP clients to perform Pulumi operations like retrieving package information, previewing changes, deploying updates, and retrieving stack outputs programmatically.

Multi-cloud pricing comparison across AWS, Azure, GCP, and OCI with 2,700+ instance types. Real-time pricing from public APIs, workload calculators, and migration savings estimator.

A powerful MCP server that enables AI assistants to seamlessly interact with Portainer instances, providing natural language access to container management, deployment operations, and infrastructure monitoring capabilities.

Read-only VMware vSphere/vCenter monitoring — inventory, alarms, events, host health, VM info, and snapshot listing. 8 strictly read-only tools with code-level zero-destructive guarantee (validated by test fixtures).

Deploy AI-generated HTML/CSS/JS to an instant public HTTPS URL from any MCP agent (Claude Code, Codex, Cursor, Kiro, Copilot). Remote HTTP MCP endpoint with OAuth 2.1 device-flow login — no API key to mint or store.

Install and manage a self-hosted XNS Relayer — S3-compatible object storage on a decentralized provider network with $0 egress. 15 tools covering prerequisites, account registration, install, claim, health, VPD configuration, S3 verification, CLI credentials, settings, restart, and backups. `npx @xns-cloud/relayer-mcp`

Deploy static HTML folders to permanent vibie.page URLs in seconds. One-line auto-install (`npx vibie-mcp setup`) wires up Claude Desktop and Cursor, OAuth device-flow auth, automatic folder marker for repeat deploys without re-typing slugs.

AWS Single Sign-On (SSO) integration enabling AI systems to securely interact with AWS resources by initiating SSO login, listing accounts/roles, and executing AWS CLI commands using temporary credentials.

Publish agent-made artifacts (HTML, Markdown, CSV, Mermaid) to temp.md — one stable public link that updates in place. Anonymous publish with no API key, activity-based expiry with restore. Install: `npx tempmd-mcp`.

integrates with the fastmcp library to expose the full range of NebulaBlock API functionalities as accessible tools

Provides MCP multi-cluster Kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources.

Azure FinOps infrastructure cost optimization: idle resources, rightsizing, and Reserved Instance recommendations for Claude Code.

OpenShift & Kubernetes operations — projects, pods, logs, deployments/deploymentconfigs, routes, services, builds; scale, rollout-restart, apply and delete — governed with read-only/read-write/admin modes, namespace allowlists, protected namespaces, apply/delete gating, dry-run, Secret redaction, and typed confirmation. Connect with a web-console token or username/password (local IdP). `npx -y @dockndevai/mcp-openshift`

The most complete Cloudflare MCP — 69 tools over the REST API v4 (DNS, Zones, Workers, KV, R2, D1, Pages, WAF, SSL, Email Routing, Logpush, Workers AI) in a single local stdio server, with a server-side human-approval gate on every mutation. `npx -y cloudflare-mcp-pro`.

MCP server for the Rancher ecosystem with multi-cluster Kubernetes operations, Harvester HCI management (VMs, storage, networks), and Fleet GitOps tooling.

A bridge that exposes any Spinnaker instance as an MCP server via the Gate API, enabling management of applications, pipelines, executions, and cloud infrastructure.

A Model Context Protocol server that integrates with Tilt to provide programmatic access to Tilt resources, logs, and management operations for Kubernetes development environments.

Go-based MCP Server for interfacing with Nutanix Prism Central resources.

Create, modify, and delete different aspects of [Liveblocks](https://liveblocks.io) such as rooms, threads, comments, notifications, and more. Additionally, it has read access to Storage and Yjs.

Anchor AI FinOps to real, live cloud pricing. 15 tools for AWS, GCP & Azure — public list prices and enterprise negotiated rates (Reserved Instances, Savings Plans, CUDs, EDPs). No credentials needed for AWS and Azure public pricing. `pip install opencloudcosts`

Multi-cluster Kubernetes monitoring & operations (pods, logs, deployments, scale/restart, apply, exec) — safe-by-default access modes, namespace/context allowlists, delete/apply/exec gating, dry-run, audit. `npx -y @dockndevai/mcp-kubernetes`

The best way to deploy cloud infrastructure using Claude Code and MCP.

AI-native platform for Kubernetes management and automated GitOps (30+ tools).

An MCP to give access to all Netskope Private Access components within a Netskope Private Access environments including detailed setup information and LLM examples on usage.

A lightweight yet robust server that empowers AI assistants to securely execute Kubernetes CLI commands (`kubectl`, `helm`, `istioctl`, and `argocd`) using Unix pipes in a safe Docker environment with multi-architecture support.

A Model Context Protocol (MCP) server for Kubernetes that enables AI assistants like Claude, Cursor, and others to interact with Kubernetes clusters through natural language.

MCP server for Spot.io (Spotinst) API with 23 tools for managing Ocean clusters, VNGs, Elastigroups, costs, right-sizing, and logs across AWS and Azure with multi-account support.

Access Cloudeval project context and reports for cloud evaluations and reviews. Supports Azure and static AWS CloudFormation evaluation (beta); includes a read-only toolset and requires authentication.

MCP server for the Portkey AI Gateway Admin API — 150 tools for prompts, configs, analytics, keys, guardrails, integrations, and more.

Governed Kubernetes operations (k3s/EKS/GKE/AKS) — workloads, batch jobs, config, storage, networking, and rollout management (55 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

CNCF release intelligence: typed, quoted facts (security fixes, breaking changes, deprecations) from every graduated/incubating project's release notes, updated daily. check_stack compares running versions locally so they never leave your process.

A VMware ESXi/vCenter management server based on MCP (Model Control Protocol), providing simple REST API interfaces for virtual machine management.

Publish a page, a file, or a folder to a public URL. Two tools: `publish_html` for content written in the chat, and `publish_path` for something already on disk — folder structure preserved, no need to zip first. Publishing is anonymous by default; no account or API key required. `npx -y plopino`

Azure Resource Manager inventory, tags, VM power & lifecycle — governed with subscription/resource-group allowlists, protected groups, location allowlist, delete gating, and typed confirmation. `npx -y @dockndevai/mcp-azure`

Manage domains, DNS records, contacts, marketplace listings, and more via the Spaceship API

Compare on-demand compute, block/object storage, managed Postgres, egress & GPU pricing across AWS, Azure, GCP, and OCI, plus FinOps decision tools (RI/Savings Plan break-even, multi-cloud workload TCO, exit-cost migration analysis, and egress arbitrage). 25 tools.

An MCP server implementation for 4EVERLAND Hosting enabling instant deployment of AI-generated code to decentralized storage networks like Greenfield, IPFS, and Arweave.

Deploy and manage static sites from AI agents. A simpler alternative to Vercel and Netlify for static website hosting — upload files, get a URL, and connect custom domains.

MCP-K8S is an AI-driven Kubernetes resource management tool that allows users to operate any resources in Kubernetes clusters through natural language interaction, including native resources (like Deployment, Service) and custom resources (CRD). No need to memorize complex commands - just describe your needs, and AI will accurately execute the corresponding cluster operations, greatly enhancing the usability of Kubernetes.

Manage your entire Sevalla cloud infrastructure from AI agents. Hosted remote server with OAuth — connect in one click, no API keys to configure.

Hosted MCP endpoint for Hostodo VPS management: list VM details, power-control, rename, reinstall from OS templates, toggle per-VM exec, run bounded/async guest-agent commands, and upload/install artifacts with scoped tokens and audit logs.

A Kubernetes Model Context Protocol (MCP) server that provides tools for interacting with Kubernetes clusters through a standardized interface, including API resource discovery, resource management, pod logs, metrics, and events.

Manage Hetzner DNS zones and records through the current Hetzner Cloud API (the legacy `dns.hetzner.com` API was shut down in May 2026). 22 tools: zone and RRSet CRUD, zonefile import/export, TTL and protection changes, primary nameservers, and async action tracking. Every destructive tool requires an explicit `confirm`. `npx -y hetzner-dns-mcp`

Official Backblaze B2 MCP server for buckets, files, keys, Object Lock, and S3-compatible storage. `npx -y @backblaze-labs/b2-mcp`

The official NetLicensing MCP Server is a natural language interface that enables agentic applications to manage the full software licensing lifecycle in Labs64 NetLicensing without writing a single API call.

Manage Dynadot domains, DNS, WHOIS, nameservers, transfers, and aftermarket through 10 AI-friendly composite tools. Install with `npx -y domain-mcp`.

This is an MCP server used for querying books, and it can be applied in common MCP clients, such as Cherry Studio.

Manage pfSense firewalls through AI assistants — firewall rules, DHCP leases/reservations, DNS overrides, gateway monitoring, ARP table, and service management. 17 tools with two-step confirmation for destructive operations.

Manage your Redis Cloud resources effortlessly using natural language. Create databases, monitor subscriptions, and configure cloud deployments with simple commands.

MCP server for the [Gozargah/Marzban](https://github.com/Gozargah/Marzban) proxy/VPN panel API, built on the typed `marzban-sdk` client. 21 tools across users, subscriptions, nodes, hosts, config and system stats, plus 3 investigation prompts. Env-only credentials (never a tool argument), profile-gated tool visibility (`readonly`/`standard`/`full`), and a one-time confirmation token required before any destructive call. `npx -y marzban-mcp` or Docker `ilmar7786/marzban-mcp`.

MCP Server for Azure Data Lake Storage. It can perform manage containers, read/write/upload/download operations on container files and manage file metadata.

**LUNO — AI Backend Platform** ([luno.rest](https://luno.rest)): hosted SaaS backend (CMS, Forms, Auth, Storage) for Claude Code, Cursor, and Codex. Not the cryptocurrency Luno exchange MCP. Registry: `io.github.luno-cms/mcp`.

Agent-first web host: publish a static site or edge function to the web in one call (no account), then manage updates, custom domains, SSL, env vars, databases, and email. Hosted remote MCP at https://shiply.now/mcp.

powerful Kubernetes MCP server with additional support for OpenShift. Besides providing CRUD operations for **any** Kubernetes resource, this server provides specialized tools to interact with your cluster.

VMware NSX network management — Segments, Tier-0/Tier-1 Gateways, NAT rules, static/BGP routing, and IPAM pools. 33 tools with dry-run preview, port-count safety checks, and double-confirmation for delete operations.

A MCP built on Qiniu Cloud products, supporting access to Qiniu Cloud Storage, media processing services, etc.

Cloud infrastructure analysis for AI coding assistants — detects IaC drift, missing indexes, security gaps, and performance anti-patterns across AWS services and databases. 13 tools, works with Claude Code and Cursor.

Oracle Cloud (OCI) live resource discovery, dependency mapping & reproducible Terraform generation — read-only and secret-redacting. `npx -y @dockndevai/mcp-oci`

VMware NSX security — Distributed Firewall policies/rules, Security Groups, Traceflow troubleshooting, and IDS/IPS profiles. 20 tools with active-rule checks before policy deletion and reference-count validation for security groups.

A MCP server that enables AI assistants to operation resources on Alibaba Cloud, supporting ECS, Cloud Monitor, OOS and widely used cloud products.

Local-first FinOps copilot. Connect AWS, Azure, GCP, Kubernetes, and 15+ SaaS and AI bills, then ask cost questions in Claude or Cursor, find waste, and get the fix as a pull request you approve. Read-only; your credentials and bill stay on your machine. `uvx nable`.

Build and run a complete backend from your agent on the Anythink platform: relational data with row-/field-level security, full-text + semantic + geo search, RBAC + BYOK, a workflow/automation engine, a growth & retention engine (email, actionable push, promotions, per-user referral codes + rewards, points/credits), payments + marketplace billing, and a growing catalog of integrations (Claude, OpenAI, Slack, Google, GitHub…) — driven through one CLI-backed MCP tool. Install with `npx -y @anythink-cloud/mcp`.

Deploy and manage [BasicDeploy](https://basicdeploy.com) containers, each with a PostgreSQL database, S3-compatible object storage, env vars, and a public URL provisioned automatically. Create containers, deploy apps (Node/Python/Go/Docker, auto-detected), run commands, read logs, and toggle always-on. Install: `npx -y basicdeploy-mcp`.

Track LLM token costs across Claude, GPT and Gemini. MCP server + CLI with optimization hints and $ savings estimates. 📇🏠

VMware Tanzu / vSphere Kubernetes Service — Supervisor cluster, Namespace, and TKC (Tanzu Kubernetes Cluster) lifecycle management. 20 tools with dry-run mode, kubeconfig export, and double-confirmation for namespace/TKC deletion.

Portkey Admin API control-plane MCP server with 181 tools across 20 domains, including prompts, configs, keys, analytics, guardrails, integrations, and deployments.

Kubernetes cluster operations through MCP

MCP server for Appcircle: exposes Build, Signing Identities, Testing Distribution, Enterprise App Store, Publish to Stores, and Reporting tools to any MCP-capable client (Claude Desktop, Cursor, VS Code, etc.). The Appcircle MCP Server acts as the bridge between AI tools and Appcircle; thus, AI agents, assistants and chatbots to safely access and interact with Appcircle resources through structured, governed, and task-level tools. - CI/CD and Workflow Intelligence: Monitor pipeline runs, track release status, and get insights into your mobile CI/CD workflows. - Configuration and Environment Insights: Query build configurations and signing setup to understand how a project is configured and where issues may originate. - Reporting and Operational Insights: Generate summaries of CI stability, recurring issues, pipeline performance, and overall CI/CD health.

6 tools · get_build_insights_report, get_build_status

Model Context Protocol (MCP) server for AWS Documentation This MCP server provides tools to access AWS documentation, search for content, and get recommendations. - Read Documentation: Fetch and convert AWS documentation pages to markdown format - Search Documentation: Search AWS documentation using the official search API (global only) - Read Sections: Fetches sections of AWS documentation page and converts it to markdown format. - Search Table: Filter and search rows in large documentation tables (e.g., service quotas, pricing) without reading the full page (global only) - Recommendations: Get content recommendations for AWS documentation pages (global only) - Get Available Services List: Get a list of available AWS services in China regions (China only)

5 tools · read_documentation, read_sections

The official developer experience MCP Server for Amazon DynamoDB. This server provides DynamoDB expert design guidance and data modeling assistance. > [!IMPORTANT] > Generative AI can make mistakes. You should consider reviewing all output generated by your chosen AI model and agentic coding assistant. See AWS Responsible AI Policy. The DynamoDB MCP server provides eight tools for data modeling, validation, cost analysis, and code generation: - dynamodb_data_modeling - Retrieves the complete DynamoDB Data Modeling Expert prompt with enterprise-level design patterns, cost optimization strategies, and multi-table design philosophy. Guides through requirements gathering, access pattern analysis, and schema design.

6 tools · compute_performances_and_costs, dynamodb_data_model_schema_converter

Attack Surface Scan ships a hosted MCP server, so Claude and other AI agents can run scans, read findings, watch the change feed, triage and pull PDF reports. All of it in chat, against the domains your account has verified, with nothing to install and no API keys to manage. Every client follows the same handshake: point it at the endpoint, a browser window opens Attack Surface Scan's consent page, sign in and click Allow access. You need a Attack Surface Scan account (the trial works) but no keys or extra setup.

6 tools · assign_domain_client, get_report

Publish static sites from your AI chat with one tool call — no account.

Device-code registration, scoped access, a per-scope approval valve & instant revoke, machine-readable discovery (auth.md, llms.txt, OpenAPI, and the SKILL.md workflow), and the MCP server with 18 tools — the reads, public-site image analysis + savings estimates, project creation, cache purge, domain verification, and every production mutation behind a sensitive scope: hostname activation, adding funds, origin configuration, project archive, and applying the delivery configuration. Each runs on its own for an autonomous agent — except money, which always waits for your approval — or opens an approval card when you ask to be in the loop. The published @cdnmn/cli + @cdnmn/sdk let an agent detect, configure, rewrite, test, and verify straight from the project — honoring the repo’s AGENTS.md.

6 tools · analyze_website, create_project

Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows

One-stop backend services for WeChat Mini-Programs and full-stack apps. Provides specialized MCP tools for serverless cloud functions, databases, and one-click deployment to production with China market access through WeChat ecosystem.

6 tools · Configure auth & storage, Deploy cloud functions

Integration with Cloudflare services including Workers, KV, R2, and D1

5 tools · Build Workers apps, Debug app logs

This repository provides a Model Context Protocol (MCP) server that exposes the Dacast video platform API as a set of structured MCP tools. It lets MCP-compatible clients (such as Claude Desktop) manage Dacast resources — channels, playlists, images, simulcast destinations, and more — through natural language. - StdIO-based MCP server - Speaks the Model Context Protocol over standard input/output. - Designed to be launched by an MCP client process and kept running as a child process. - Dacast API integration - Channel management: create, list, get, update. - Playlist management: create, list, get, update, set playlist content. - Image management: thumbnails and splash images. - Simulcast destination management: create, get, delete.

4 tools · create_channel, create_playlist

The DataFast MCP server lets MCP-compatible clients such as Codex, Claude Code, and Cursor query your analytics and manage your account through natural language. It provides the same functionality, permissions, and safety checks as the REST API and CLI. It uses Streamable HTTP at https://datafa.st/api/mcp. Open Account Settings → API / MCP, choose which websites and permissions the client can access, then create a token. Copy the dft_ token when it appears—you will use it in the next step, and it is only shown once.

6 tools · Check integration status, datafast_analytics_overview

Connect the DMARC MCP server to Claude, Cursor, VS Code or any MCP client and ask your AI assistant about your DMARC aggregate reports, failing senders, DNS history and TLS reports, in plain language. Sign in once: DNS, DMARC, DKIM and SPF lookup tools then work for any domain, no subscription needed. Full per-client instructions live at app.dmarcdkim.com/mcp-instructions Two sets of tools over one MCP server, both behind a single sign-in: account tools that read your stored DMARC data, and free lookup tools that work for any domain with no subscription.

6 tools · Identify failing senders, Inspect TLS-RPT reports

Registration Domain Name, Website and Biolink

By implementing MCP, Elastic Email allows AI agents to access and control your email operations while maintaining security and proper authentication. - Add contact to a list - Upload and add contacts - Create a list - Create a segment - Create a campaign - Get campaigns - Update a campaign - Pause a campaign - List campaigns - Send emails: both transactional and bulk - Fetch contact, contacts, contact from list - Fetch lists - Fetch templates - Fetch segments - Is ready (health check, connection and readiness check) - Delete contact from list - Delete contact from account

5 tools · add_contact, Build campaigns

The Elementary MCP Server allows you to connect your Elementary environment to any client that supports MCP (Model Context Protocol). This lets AI agents, copilots, or natural language interfaces query and act on your data stack using live context. MCP (Model Context Protocol) is an open protocol introduced by Anthropic. It defines a way for AI systems to retrieve context and trigger actions from external tools in a structured way. The Elementary MCP Server exposes an interface to query key parts of your data environment — including:

6 tools · get_execution_history, get_incidents

> MCP Server for Realtime and Historical Currency Data You can now give Codex / ChatGPT / Claude / Gemini etc. (any Agent/AI/LLM that supports the Model Context Protocol standard) access to all the same top-grade Currency & FX data you access via our APIs. The 7-day free trial and all our paid plans include access to your subscription via our remote MCP Servers. Make sure you sign up for an account at https://console.fastforex.io OpenAI Codex ChatGPT Claude Desktop Claude Code Google Gemini CLI OpenCode Cursor

7 tools · convert, crypto_fetch_prices

A workspace where you, your team, AI Agents and MCP servers collaborate to build, manage, and publish for the internet. From idea to live website in three simple steps, with AI handling the heavy lifting. Start with a beautiful, ready-to-use template, or easily revamp your existing website by moving it over to Hostbento. Jump into Workspaces to fine-tune your design, write content, and plan marketing campaigns alongside your AI assistant. Focus entirely on your website. Hosting, security, performance, and updates are completely taken care of for you.

4 tools · Collaborate in Workspaces, Migrate an existing site

Container image for the kubernetools MCP server. Registry: ghcr.io/kubernetools/mcp-server No authentication required; all connections are rate-limited per source IP at the free-tier limit. echo '[{"key":"mykey","tier":"free"}]' > keys.json podman run -d \ -p 3000:3000 \ -v "$(pwd)/keys.json:/keys.json:ro" \ -e K8S_VERSIONS=v1.33,v1.34,v1.35,v1.36 \ -e KEY_STORE_PATH=/keys.json \ ghcr.io/kubernetools/mcp-server:latest The key store is a flat JSON array loaded once at startup: Every request must include the key in the Authorization header:

4 tools · get_resource, get_type

Enable Claude to be your everyday sales prospector. Enrich contacts and companies with verified business data directly from Claude and other MCP-compatible AI agents. Get detailed person and company information including emails, phone numbers, job titles, company details, and social profiles. - Email Enrichment: Look up detailed person and company data using an email address - LinkedIn Enrichment: Look up detailed person and company data using a LinkedIn profile URL - Email Validation: Verify if an email address is deliverable, check format validity, and assess risk level - Rich Data: Returns verified business emails, phone numbers, job titles, company info, and social profiles - No Match = No Charge: Enrichment credits are only consumed when a profile match is found

3 tools · email_enrich, email_validation

> For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs; this page is available as Markdown. The MetricFire MCP Server allows supported AI clients to interact directly with your Hosted Graphite account using the Model Context Protocol (MCP). Once connected, clients such as GitHub Copilot, Cursor, Claude/Claude Code, etc. can use Hosted Graphite APIs for metric discovery, Graphite rendering, alert management, notification channels, scheduled mutes, and other monitoring workflows.

5 tools · Handle notification channels, Manage alerts

Find, buy, and manage your domains without leaving chat

An SSE-based MCP server that allows LLM-powered applications to interact with OCI registries. It provides tools for retrieving information about container images, listing tags, and more.

4 tools · get_image_config, get_image_info

DataGrout's Oracle MCP Server connects AI agents to Oracle Fusion Cloud through OAuth2, using DataGrout's application credentials or your own. Write operations are disabled by default and require explicit configuration per integration. 1000+ tools cover Financials, Procurement, Inventory, Suppliers, Tax, and Workforce, individually selectable rather than exposed as one fixed set. Go to the DataGrout GitHub and set up using command line interface - <u>https://github.com/DataGrout/conduit-sdk</u> 1. Sign up for a DataGrout account Go to <u>https://app.datagrout.ai/</u> and create an account.

6 tools · Access workforce records, Check inventory levels

European cloud hosting. Use your favorite AI coding assistant to easily deploy and manage apps on Ploi Cloud.

Enable real-time access to CRM, ERP, databases, and more via a secure, no-code MCP Server—designed for AI chatbots and LLMs Skyvia MCP Endpoint is a no-code gateway that makes your business data accessible to AI assistants in real time. Built on the open Model Context Protocol (MCP), it enables tools like Claude to understand and query data from your data source—with no APIs or schemas to manage. No dev work. No setup overhead. Just connect and chat. Skyvia MCP Endpoint connects AI assistants directly to your data—in real time and securely. It helps analyze, summarize, and act on data instantly.

4 tools · Connect live business data, Generate on-demand reports

Soundside exposes 19 MCP tools for generating, editing, composing, extracting, and analyzing media — images, video, audio, music, text, and business artifacts — plus LoRA adapter fine-tuning and server-side video composition. Connect any MCP client. Pay with an API key (credits) or crypto (x402 USDC on Base, no account needed). > Currency 2026-08 (2026-08-23) > - Removed: Luma (entirely) and Runway image/video generation. Runway is now audio-only — TTS and sound effects via create_audio. > - Added: Lyria 3 music generation (create_music), Grok TTS (create_audio), Grok per-second × resolution video pricing, Alibaba Wan 2.7 video models (international default), MiniMax H3 video adapter. > - Provider and pricing data below matches the live x402 catalog: GET https://mcp.soundside.ai/api/x402/status.

5 tools · analyze_media, create_image