Remote MCP server that audits a website's readiness for AI agents, returning a 0-100 score, grade and agent-simulation report.
What you can do
Scan a site URL for AI-agent readiness across the engine's AR-* checks, such as robots.txt AI policy, llms.txt, agent.json, JSON-LD, OpenAPI and MCP/OAuth discovery
Run a full audit that adds an agent-simulation task (for example finding pricing) and an industry benchmark percentile
Receive a persisted report with score, grade and simulation results
When to use it
Useful when you want to check how discoverable and usable a site is for AI agents, compare it against industry benchmarks, or verify changes to robots.txt, llms.txt or discovery files after an update.
Requirements
A remote streamable HTTP endpoint at ainative.ax; no authentication, environment variables or headers are declared. The audited site must be reachable over the network.
Before you install
Audits are run against URLs you supply, so the server fetches those sites on your behalf. Full audit results are persisted server-side, so avoid submitting internal or non-public URLs you do not want stored.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.AINative-Studio%2Fax-audit/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Run an AX Audit on a URL — scores how ready a website is for AI agents across every real AR-* check this engine runs (robots.txt AI policy, llms.txt, agent.json, JSON-LD, OpenAPI, MCP/OAuth discovery, AR-PROV provisioning, and more — the exact check count grows over time, so it is intentionally not pinned here). Returns a 0-100 score, a letter grade, and a per-check breakdown. No authentication required.
Parametersurlrequired
run_full_audit
Run full AX Audit with simulation and benchmark
Run the full AX Audit on a URL — the same real AR-* checks as scan_site (the exact check count grows over time, so it is intentionally not pinned here), plus an agent-simulation task (e.g. "find pricing") and an industry benchmark percentile, with the result persisted server-side. Returns a report_id that can be used to retrieve the same report later without re-scanning. No authentication required.
Parametersurlrequiredindustry
Version history
1
v1.0.0LatestOct 29, 2026
Score
75%
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.