mcp-mozilla-observatory

@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 1683+ live data sources.

Tools

• observatory_scan(host) — runs (or returns Mozilla's recent) scan and gives the letter grade A+..F, the numeric score, and the pass/fail counts.
• observatory_results(host, only_failures?, include_history?, history_limit?) — all 12 tests with pass/fail, score impact, Mozilla's own remediation prose, the observed response headers, and the host's grade history.
• observatory_grade_distribution() — how many scanned sites hold each grade, so a single grade can be placed against the web at large.

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

• The detail endpoint is /analyze, not /scan. GET /api/v2/scan?host= is a 404 — /scan exists only as a POST. /api/v2/tests?scan=<id> and /api/v2/scan/<id> are both 404 as well (all verified 2026-09-17). The histogram is grade_distribution with an underscore; the hyphenated spelling 404s.
• tests_failed and pass: false disagree, and both are right. Mozilla counts only score-reducing failures in tests_failed, but sets pass: false on informational tests with a score_modifier of 0 too — mozilla.org on 2026-09-17 reported tests_failed: 2 with four tests marked not-passing. The pack returns a per-test penalized flag and a tests_failing_with_score_impact count rather than dropping the zero-impact rows, so only_failures returning more rows than tests_failed is expected and explained in the payload.
• recommendation and score_description are HTML fragments. Stripped to prose before returning.
• A host that does not resolve comes back as a 200 with a populated error field rather than an HTTP error; the pack raises on it.

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 — 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:

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

Both URLs reach the same gateway and the same 1683+ 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

curl -X POST https://gateway.pipeworx.io/v1/tools/observatory_scan \
  -H 'Content-Type: application/json' \
  -d '{"host":"mozilla.org"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/observatory_scan. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "mozilla-observatory": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-mozilla-observatory"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-mozilla-observatory

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Mozilla Observatory data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT