About CSS SOTA
What CSS you can actually ship today, from live Baseline data and MDN browser-compat-data
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://css-sota-mcp.lusrodri.workers.dev/mcpclaude mcp add --transport http lusrodri-css-sota https://css-sota-mcp.lusrodri.workers.dev/mcp{"mcpServers":{"lusrodri-css-sota":{"type":"http","url":"https://css-sota-mcp.lusrodri.workers.dev/mcp"}}}Open in Cursor{"servers":{"lusrodri-css-sota":{"type":"http","url":"https://css-sota-mcp.lusrodri.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"lusrodri-css-sota":{"type":"http","url":"https://css-sota-mcp.lusrodri.workers.dev/mcp"}}}{"mcpServers":{"lusrodri-css-sota":{"serverUrl":"https://css-sota-mcp.lusrodri.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
6| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | Maximum number of features to return. |
| query | string | No | Free-text search over feature names and descriptions, e.g. "container queries", "anchor", "scroll". Omit to list all CSS features matching the other filters. |
| since | string | No | Only features that became Baseline Newly available on or after this date (YYYY-MM-DD). Combined with `baseline`, this means "went Newly in this range AND is status X today". |
| until | string | No | Only features that became Baseline Newly available on or before this date (YYYY-MM-DD). |
| baseline | enum | No | Filter by Baseline status: "widely" (interoperable for 30+ months, safe to use), "newly" (interoperable across all major engines recently), or "limited" (not yet available across all major engines).limited | newly | widely |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.