W3c

W3C MCP — web-standards lookup over w3c/browser-specs (GitHub, CF-reachable).

Open source Repository Open in the app JSON README (API)

About

W3C MCP — web-standards lookup over w3c/browser-specs (GitHub, CF-reachable).

Details

Kind: MCP servers
Topic: Version control
Publisher: pipeworx-io
Origin: official
Category: ferramentas
Transport: http
Version: 0.1.1
Last push: 2026-08-26T17:34:02Z
Repository state: ativo
Language: TypeScript
License: MIT
Added: 2026-08-29 04:01:12
Updated: 2026-08-29 04:01:12
Origin id: io.github.pipeworx-io/w3c

README

# mcp-w3c

W3C MCP — web-standards lookup over w3c/browser-specs (GitHub, CF-reachable).

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.

## Tools

| Tool | Description |
|------|-------------|
| `w3c_search` | Find W3C / web-standards specifications by keyword or topic — HTML, CSS, WCAG accessibility, DOM, SVG, WAI-ARIA, WebAuthn, Fetch, and 800+ others. Answers "what W3C spec defines X", "the CSS grid specification", "web accessibility standard", "which spec covers custom elements". Returns specs with shortname, title, status (Recommendation / Working Draft / Living Standard), organization, and official URL. Example: w3c_search({ query: "flexbox" }). |
| `w3c_spec` | Detail for one web-standards spec by shortname ("WCAG21", "css-grid-1", "html") or title fragment ("web content accessibility"). Returns title, status, organization (W3C/WHATWG), working groups, series, official URL, editor's-draft URL. Example: w3c_spec({ spec: "WCAG21" }). Accepts shortname/name/title too. |

## Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

```json
{
  "mcpServers": {
    "w3c": {
      "url": "https://gateway.pipeworx.io/w3c/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/w3c/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:

```json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}
```

Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.

## Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:

```
ask_pipeworx({ question: "your question about W3c data" })
```

The gateway picks the right tool and fills the arguments automatically.

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT