Mozilla Observatory MCP server

@pipeworx/mozilla-observatory

MDN HTTP Observatory — grade any website's HTTP security headers and get the specific fixes, from Mozilla's public scanner.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

the letter grade A+..F, the numeric score, and the pass/fail counts.

• observatory_scan(host) — runs (or returns Mozilla's recent) scan and gives

all 12 tests with pass/fail, score impact, Mozilla's own remediation prose, the observed response headers, and the host's grade history.

• observatoryresults(host, onlyfailures?, includehistory?, historylimit?) —

so a single grade can be placed against the web at large.

• observatorygradedistribution() — how many scanned sites hold each grade,

Auth

Keyless.

Data sources

• POST https://observatory-api.mdn.mozilla.net/api/v2/scan?host= — scan summary.
• GET https://observatory-api.mdn.mozilla.net/api/v2/analyze?host= — full detail.
• GET https://observatory-api.mdn.mozilla.net/api/v2/grade_distribution — histogram.

Things the next person would otherwise rediscover

is a 404 — /scan exists only as a POST. /api/v2/tests?scan= and /api/v2/scan/ are both 404 as well (all verified 2026-09-17). The histogram is grade_distribution with an underscore; the hyphenated spelling 404s.

• The detail endpoint is /analyze, not /scan. GET /api/v2/scan?host=

counts only score-reducing failures in testsfailed, but sets pass: false on informational tests with a scoremodifier of 0 too — mozilla.org on 2026-09-17 reported testsfailed: 2 with four tests marked not-passing. The pack returns a per-test penalized flag and a testsfailingwithscoreimpact count rather than dropping the zero-impact rows, so onlyfailures returning more rows than tests_failed is expected and explained in the payload.

• testsfailed and pass: false disagree, and both are right.** Mozilla

prose before returning.

• recommendation and scoredescription are HTML fragments.** Stripped to

field rather than an HTTP error; the pack raises on it.

• A host that does not resolve comes back as a 200 with a populated error

Quick Start

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

{
  "mcpServers": {
    "mozilla-observatory": {
      "url": "https://gateway.pipeworx.io/mozilla-observatory/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/mozilla-observatory/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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:

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

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

Shortened. The full README is on GitHub.