Aso Audit MCP

aso-mcp — the free Agent Readiness Scanner

What's your ASO score?

SEO made you visible to search engines. ASO (Agent Signal Optimization) makes you discoverable, trustable, and payable by the AI agents that are becoming the web's next visitors.

aso-mcp is the free, open-source ASO Scanner — an MCP server that scans any website and produces an Agent Readiness Report scored on the open ASO framework. The beta npm package is @forgemeshlabs/aso-audit-mcp.

This release tracks Google's current agent-readiness guidance without overstating it: Google Search says traditional SEO fundamentals still apply to generative AI search, llms.txt is ignored by Google Search itself, and browser agents benefit from clean DOM, screenshot, and accessibility-tree signals. The scanner keeps llms.txt because non-Google agents use it, and adds a browser-agent UX check for semantic controls, linked labels, ARIA/role fallbacks, and hidden-overlay risk.

Beta. Experimental ASO scanner for evaluating whether agents can discover, trust, understand, and use a website/API/tool. ASO scoring is experimental and will evolve as agent standards mature.

=== Agent Readiness Report: https://example.com ===

ASO Score: 70/100 Agent Readiness: Ready Level: ASO-4 Trustable — Agents can verify trust, reputation, and operational signals.

Discoverability 20/20 Identity 15/20 Trust 11/15 Commerce 5/15 Reputation 4/15 Memory 15/15

What it checks — 34 signals across 6 pillars

Find gaps in discovery, trust, interoperability, and commerce — every emerging agent standard in one scan:

Deterministic x402 v2 endpoint audit

The MCP tool audit_x402_endpoint complements the origin-wide ASO scan with a no-spend protocol audit of one paid endpoint. It returns a 0-100 score, A-F grade, compliance verdict, per-check booleans, failed checks, and observed schemes/networks/extensions. It validates the live 402 challenge but never sends PAYMENT-SIGNATURE, so it cannot authorize or settle a payment.

Checks: HTTPS/TLS, HTTP 402, PAYMENT-REQUIRED, Base64 JSON, x402Version: 2, non-empty accepts, CAIP-2 networks, required payment fields, and JSON content type. For body-gated routes, pass method, body, and optionally content_type.

This is deliberately reported separately from the ASO Score: protocol compliance does not prove discoverability, trust, settlement, idempotency, or paid-response quality.

Living standards model

Agent protocols are changing quickly. The scanner is maintained as part of a living framework: checks are versioned, and stable standards, optional capabilities, release candidates, drafts, and vendor conventions are labeled separately. See the dated scanner source list and the canonical ASO source registry.

Every check returns pass / partial / fail with concrete evidence and a fix recommendation. Results roll up into the six ASO pillars (Discoverability 20, Identity 20, Trust 15, Commerce 15, Reputation 15, Memory 15) → your ASO Score and maturity level.

Install

Requires Node.js ≥ 20. Published on npm as @forgemeshlabs/aso-audit-mcp — no clone or build needed.

npm install -g @forgemeshlabs/aso-audit-mcp

Or skip the install entirely and run it with npx (recommended for MCP clients):

npx -y @forgemeshlabs/aso-audit-mcp

Claude Code

claude mcp add aso -- npx -y @forgemeshlabs/aso-audit-mcp

Claude Desktop / Cursor / Windsurf (any MCP client)

{

"mcpServers": { "aso": { "command": "npx", "args": ["-y", "@forgemeshlabs/aso-audit-mcp"] } } }

Development (from source)

Only needed if you're hacking on the scanner itself:

git clone https://github.com/forgemeshlabs/aso-audit-mcp

cd aso-audit-mcp npm install && npm run build claude mcp add aso -- node /path/to/aso-audit-mcp/dist/index.js

Tools

Try it: *"Scan example.com for agent readiness"* · *"What's my ASO score?"* · *"Give me a fix plan to make my site agent-ready."*

CLI smoke test (from a source checkout)

npm run smoke -- https://your-site.com

Glama / registry metadata

This repository includes glama.json for Glama MCP registry ownership and install metadata.

• Package: @forgemeshlabs/aso-audit-mcp
• Current release: v0.4.4
• Transport: local stdio
• Authentication: none required for local stdio use. The scanner does not ask for API keys, tokens, cookies, or third-party credentials.
• HTTP deployment: not enabled by this npm package. Any public HTTP deployment of this scanner must add authentication, per-client rate limits, request logging, and an egress policy before exposure.

Recommended Glama/MCP install command:

npx -y @forgemeshlabs/aso-audit-mcp

Example usage after connecting the server to an MCP client:

Scan https://example.com for agent readiness.

Give me the ASO fix plan for example.com. Check only the llms-txt signal for example.com. List the ASO scanner checks.

Release verification:

• Git tag: v0.4.4
• npm package: @forgemeshlabs/aso-audit-mcp
• MCP server version: 0.4.5 (read from package.json at startup)

Since v0.2.0 the server includes the deterministic no-spend x402 v2 endpoint compliance audit while preserving the broader ASO Agent Readiness score as a separate metric.

Glama release build

Glama installability requires a Glama release, which is a containerized build created from the Glama Dockerfile admin page, not a GitHub release. This repo includes a production Dockerfile and GLAMA.md with the build spec values to use in Glama:

Build steps:

npm ci

npm run build npm prune --omit=dev

Runtime command:

node dist/index.js

In Glama's CMD arguments field, enter:

["node", "dist/index.js"]

Do not leave CMD arguments as []; Glama validates that field separately from the Dockerfile CMD.

The ASO framework

SEO ranks pages for people. ASO prepares services for agent selection, invocation, payment, and repeat use.

Scores from this scanner are directional self-assessments. ASO Certification (ASO-3+) requires verified evidence — see the scoring rubric and agentsignaloptimization.com for audits, certification, and the full framework.

Sponsored cards (Lulu Ads)

There is no paid ForgeMesh server behind this MCP — every tool fetches the scanned site directly — so a Lulu Ads card can only attach client-side, and only to list_tools. It is a plain, labelled data field on the JSON result, never text the model could read as an instruction:

"sponsored": { "label": "Sponsored", "text": "...", "url": "https://..." }

• This package ships no ad credentials. A card renders only when the operator running the MCP sets LULU_ADS_PUBLISHER_ID and LULU_ADS_API_KEY (both required). For an end user running npx -y @forgemeshlabs/aso-audit-mcp with no creds, the package makes zero calls to the ads network and no card ever appears.
• LULU_ADS_ENABLED=false is a kill switch. Scan/audit tools never touch the SDK.
• Fail-open: any SDK error or timeout (hard budget 2s) returns the original response unchanged. The only external host contacted by this package, other than the sites you ask it to scan, is ads.getlulu.dev. Scanned-site requests all go through the SSRF-guarded client (private-IP refusal, pinned DNS, 10 s timeout, 512 KB response cap, revalidated redirects).
• Strip it: delete result.sponsored.

Security

This scanner makes outbound requests to URLs you give it, so it is built to resist SSRF abuse:

• Scheme allow-list — only http/https; file:, ftp:, gopher:, data: etc. are rejected.
• Private-target blocking — after DNS resolution, requests to loopback, private (RFC 1918), link-local, CGNAT, reserved, multicast, and the cloud metadata address (169.254.169.254) are refused. IPv6 loopback/ULA/link-local and IPv4-mapped forms are covered too. If a hostname resolves to *any* private address, the scan is refused.
• Pinned-IP transport — each request dials the exact public IP that was validated, while TLS still verifies the original hostname. This closes the validate-then-connect DNS rebinding window.
• Manual redirect validation — automatic redirect following is disabled; every hop is re-validated against the same rules, capped at 5 redirects. A public URL that 30x-redirects to an internal address cannot slip through.
• Untrusted remote content — parsed manifests are omitted from tool output by default (include_artifacts: true to opt in, and they are then explicitly labeled untrusted); embedded text excerpts are control-char-sanitized and length-capped. Treat any returned remote content as data, never instructions.
• Bounded — GET only, ASO-Scanner/1.0 UA, max 6 concurrent, 10s timeout, 512KB body cap. Never authenticates, never POSTs, never crawls beyond well-known paths.
• Tested hardening — npm test covers unsafe URL rejection, private IP ranges, artifact sanitization, redirect blocking, redirect hop caps, and the test-only loopback escape hatch.

Deployment: stdio (local, per-user) is the safe default. A public HTTP deployment is a network-egress tool and must add authentication, per-client rate limiting, request logging, and an egress policy before exposure.

• Reputation signals (citations, reviews, success rates) cannot be auto-verified by a crawler; they are reported as manual and scored 0 until verified by audit — so the