creatica
Official Creatica MCP server (@creatica/mcp). Lets AI agents browse, describe, suggest and generate deterministic procedural SVG/PNG backgrounds. It runs locally over stdio (npx -y @creatica/mcp), and a hosted Streamable HTTP endpoint at api.creatica.app/mcp is documented in the provider's OpenAPI and advertised on the MCP install page.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
list_backgrounds— Browse the catalog of background structures, optionally filtered by free-text query, tag or mood word. Returns name, summary, mood, use cases and preview URL.describe_background— Full style card for one structure (look, mood, where text can go, tips, and every parameter with ranges and defaults), plus the JSON Schema for its generate request.suggest_backgrounds— Rank structures for a natural-language brief. Returns why each matched, matching built-in palettes, and a ready-to-run example generate_background request.list_palettes— Built-in curated colour palettes with hex colours and derived mood tags. Pass the id as palette.palette to generate_background.generate_background— Render a background as SVG or PNG. Deterministic (same structure, options and seed give the same image). With an API key in hosted mode, returns a permanent cacheable URL.list_brand_kits— Saved brand palettes on the account. Pass a kit slug as `brand` to generate_background. Registered only when an account/API key is configured (hosted mode).
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.