scalix-cloud-mcp
The agent-native cloud: provision Postgres-compatible databases, deploy services and functions in isolated microVMs, manage storage, auth and AI inference, and read logs and billing — 50 tools behind one API key. Hosted remote server; this repository carries the connection docs.
README
Scalix World — MCP Server
The official Model Context Protocol server for Scalix World, the AI-native neocloud. One hosted MCP server lets an agent operate the entire platform — no local install.
Antigravity (Google)
Install as a plugin (recommended — one command):
git clone https://github.com/scalixworld/scalix-cloud-mcp ~/.gemini/config/plugins/scalix
Then open the plugin's mcp_config.json and replace YOUR_SCALIX_API_KEY with a key from scalix.world (Console → API Keys). Antigravity auto-discovers plugins in ~/.gemini/config/plugins/ (global) or .agents/plugins/ (per-workspace).
Or add the server directly: paste the mcpServers block from mcp_config.json into ~/.gemini/config/mcp_config.json (Antigravity 2.0 / IDE) — or in Antigravity CLI type /mcp for the interactive manager. Note Antigravity uses serverUrl (not url).
Connect
https://api.scalix.world/v1/mcp
Authenticate with a Scalix World API key (Authorization: Bearer <key>), scopable
to specific services, projects, and actions. Listed in the official MCP registry as
world.scalix/cloud.
Example (Claude Code):
claude mcp add --transport http scalix https://api.scalix.world/v1/mcp \
--header "Authorization: Bearer $SCALIX_API_KEY"
What an agent can do with it
- Databases — provision Postgres-compatible databases with scale-to-zero; create copy-on-write branches to test migrations, then promote or drop them
- Compute — deploy container services and serverless functions in isolated microVMs
- Storage, Auth, DNS, Email — manage the production primitives around the app
- AI inference — run AI workloads with routing, metering, and spend controls
- Observability & billing — read logs and metrics, check usage and remaining credits; the agent can make cost-aware decisions with the same key it deploys with
Consequential actions (deletes, production changes, spend past budget caps) pause for human approval — guardrails are a platform feature, not a wrapper script.
Docs
- MCP guide: https://docs.scalix.world/mcp
- API reference: https://docs.scalix.world/api-reference/mcp
- Start free (no card): https://scalix.world
About
Scalix World is a fully managed cloud platform engineered as one system — database, AI, compute, storage, auth, billing — operable by humans through a console and by agents through this MCP server, on sovereign European infrastructure. Built by Scalix.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.