# Scalix Cloud MCP server > Operate Scalix Cloud databases, functions, storage, containers, AI inference and Linux machines from your assistant. - Listing: https://mcp.tc/i/scalix-cloud - Connect: use the server's own URL `https://api.scalix.world/v1/mcp` (with your API key); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: API key - Category: [Cloud & DevOps](https://mcp.tc/c/cloud-devops) - Vendor: Scalix - Homepage: - Repository: ## About Connects to Scalix Cloud, a hosted platform for databases, serverless functions, container services, object storage, key-value data, AI inference and persistent Linux machines. You can inspect schemas, run SQL, deploy functions and containers, manage domains and builds, run code in a sandbox, and publish events. It runs as a hosted Streamable HTTP endpoint at https://api.scalix.world/v1/mcp, with no local install. Requests need a Scalix API key sent as a Bearer token in the Authorization header. Some project and auth tools need an admin API key. Destructive SQL requires a two-step confirmation. ## What it can do - Inspect database schema, relationships and PII columns, and run SQL queries - Deploy and invoke serverless functions and container services - Scale, roll back or delete Scalix Run services - Create and use persistent Linux machines, run commands and edit files - Upload, download and list object storage and key-value data - Run AI inference and code in an isolated sandbox - Add custom domains and start container image builds ## Tools (51) - `scalix_db_relationships`: Show how tables are connected via foreign keys. (read-only) - `scalix_db_search_columns`: Search columns by name or type across all tables. (read-only) - `scalix_db_pii`: List columns classified as containing PII. (read-only) - `scalix_db_optimize`: Analyze a SQL query and suggest indexes and rewrites. (read-only) - `scalix_db_text_to_sql`: Turn a simple question into a candidate SQL query without running it. (read-only) - `scalix_db_query`: Execute SQL against the project database; destructive statements need confirmation. (can modify or delete data) - `scalix_db_schema`: Get the full schema with tables, columns, types and relationships. (read-only) - `scalix_db_table`: Get columns, indexes and foreign keys of one table. (read-only) - `scalix_db_migrate`: Apply a database migration by version number. (can modify or delete data) - `scalix_storage_list`: List buckets or objects in a bucket, with optional prefix. (read-only) - `scalix_storage_upload`: Upload base64 content to object storage. (can modify or delete data) - `scalix_storage_download`: Download an object as base64. (read-only) - `scalix_storage_create_bucket`: Create an S3-compatible storage bucket, private by default. - `scalix_fn_list`: List deployed serverless functions. (read-only) - `scalix_fn_deploy`: Deploy a serverless function from a container image. - `scalix_fn_invoke`: Invoke a deployed function with a JSON payload. (can modify or delete data) - `scalix_kv_get`: Read a value from the key-value store by exact key. (read-only) - `scalix_kv_set`: Set a key-value pair with optional TTL. (can modify or delete data) - `scalix_kv_list`: List keys, optionally filtered by prefix. (read-only) - `scalix_ai_infer`: Run AI inference with a prompt and model, billed to project credits. - `scalix_ai_models`: List AI models available for inference. (read-only) - `scalix_events_publish`: Publish an event with a type and data to a topic. - `scalix_events_topics`: List event-bus topics with IDs and names. (read-only) - `scalix_cron_create`: Create a cron schedule that runs a function or webhook. - `scalix_sandbox_run`: Run Python, JavaScript, TypeScript or Bash in an isolated sandbox. - `scalix_computer_create`: Get or create a persistent Linux machine by name. - `scalix_computer_set_ssh_keys`: Replace the SSH keys authorised for root on a machine. (can modify or delete data) - `scalix_computer_list`: List persistent Linux machines with status and resources. (read-only) - `scalix_computer_exec`: Run a command inside a running machine and return output. (can modify or delete data) - `scalix_computer_write_file`: Write a text file into a machine. (can modify or delete data) - `scalix_computer_read_file`: Read a text file from a machine. (read-only) - `scalix_computer_stop`: Stop a machine while keeping its disk and address. - `scalix_computer_start`: Start a stopped machine. - `scalix_computer_delete`: Permanently delete a machine and its disk. (can modify or delete data) - `scalix_crew_list`: List your crews with their ids and names. (read-only) - `scalix_crew_board_read`: Read a crew's notice board: every pinned note plus the newest unpinned ones, current as of this call. (read-only) - `scalix_crew_board_post`: Post a note to the crew's notice board for other members and the human to see. - `scalix_domain_add`: Add a custom domain to the project. - `scalix_domain_list`: List all custom domains and their SSL/verification status. (read-only) - `scalix_domain_verify`: Verify DNS configuration for a custom domain and provision SSL certificate. - `scalix_build_create`: Create a new container image build from a Git repository or Dockerfile. - `scalix_build_status`: Get the status and logs of a build. (read-only) - `scalix_project_create`: Create a new project within an organization. - `scalix_project_list`: List every project in an organization, with each project's ID, name, and slug. (read-only) - `scalix_auth_configure`: Configure end-user authentication for the project — require MFA, require email confirmation, and set the allowed auth providers. (can modify or delete data) - `scalix_status`: Get the current health status of the Scalix Cloud platform including all service components. (read-only) - `scalix_run_deploy`: Deploy a container service with autoscaling and a public HTTPS URL. - `scalix_run_list`: List all deployed container services in the project. (read-only) - `scalix_run_scale`: Change min and max instances of a service. - `scalix_run_rollback`: Roll a service back to an earlier revision. - `scalix_run_delete`: Permanently delete a container service. (can modify or delete data) ## Example prompts - "Show me the database schema and which columns contain PII" - "Deploy this container image as a Scalix Run service with scale-to-zero" - "Create a Linux machine called dev-box and run apt update on it" - "Roll back my api service to the previous revision" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http scalix-cloud https://api.scalix.world/v1/mcp --header "Authorization: Bearer " ``` 2. Replace the placeholder with your key before you run it, then check it with `/mcp` inside Claude Code. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Use the `mcp-remote` bridge, which keeps the key on this computer (a connector added on claude.ai with the key under **Request headers** also shows up here). Open **Settings → Developer → Edit Config** and add: `claude_desktop_config.json`: ```json { "mcpServers": { "scalix-cloud": { "command": "npx", "args": [ "-y", "mcp-remote", "https://api.scalix.world/v1/mcp", "--header", "Authorization: Bearer " ] } } } ``` 2. Replace the placeholder with your key and restart Claude Desktop. The bridge needs Node.js on your computer. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://api.scalix.world/v1/mcp`. Under **Request headers**, add `Authorization: Bearer ` with your key from Scalix, then click **Add**. 3. Turn it on in a chat from the tools menu. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "scalix-cloud": { "url": "https://api.scalix.world/v1/mcp", "headers": { "Authorization": "Bearer " } } } } ``` ### VS Code Add it to `.vscode/mcp.json`. VS Code asks for the key the first time and stores it securely: `.vscode/mcp.json`: ```json { "servers": { "scalix-cloud": { "type": "http", "url": "https://api.scalix.world/v1/mcp", "headers": { "Authorization": "Bearer ${input:api-key}" } } }, "inputs": [ { "type": "promptString", "id": "api-key", "description": "API key", "password": true } ] } ``` ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "scalix-cloud": { "serverUrl": "https://api.scalix.world/v1/mcp", "headers": { "Authorization": "Bearer " } } } } ``` 2. Refresh the MCP server list in Cascade. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add scalix-cloud --url https://api.scalix.world/v1/mcp --bearer-token-env-var SCALIX_CLOUD_API_KEY ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.scalix-cloud] url = "https://api.scalix.world/v1/mcp" bearer_token_env_var = "SCALIX_CLOUD_API_KEY" ``` Set `SCALIX_CLOUD_API_KEY` to your key in the shell that runs Codex. ### Gemini CLI ```bash gemini mcp add --transport http --header "Authorization: Bearer " scalix-cloud https://api.scalix.world/v1/mcp ``` This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "scalix-cloud": { "type": "http", "url": "https://api.scalix.world/v1/mcp", "headers": { "Authorization": "Bearer " } } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.scalix.world/v1/mcp`. ## Recent changes - 2026-10-07 19:37 UTC: 1 tool changed. Source: automatic check. Changed: scalix\_storage\_create\_bucket. - 2026-10-06 21:22 UTC: Tracking started: 51 tools read. Source: automatic check. More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/scalix-cloud#history (Atom feed: https://mcp.tc/i/scalix-cloud/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review. ## Details - Server version: 1.5.0 - MCP protocol version: 2025-06-18 - Last checked: 2026-10-07 (reachable) - Listed: 2026-10-05 - Updated: 2026-10-07 --- Source: https://mcp.tc/i/scalix-cloud (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report