Reports

Report · Attraction

How AI agents discover and act on a website

We deployed a website that exposes identical content through every interface AI agents are reported to read, and logged all traffic for five days. Discovery concentrated on the MCP server, but MCP sessions almost never progressed beyond tool enumeration. Task completion came almost entirely through hyperlinks on the HTML page, which agents executed literally.

Andromeda Agent Lab · data October 9–13, 2026 · published October 14, 2026

Observational report, not a finding. These data cover the site's first five days. No hypothesis was registered in advance, and the site was modified almost daily during collection, so no effect can be attributed to any single change. The lab's first controlled experiment on this site runs October 17–23.

Method

lab.ai-andromeda.com is a purpose-built site that serves the same content through every channel agents are reported to use:

Visitors are offered two optional actions: a daily arithmetic task, verified automatically, and a guestbook. No interface requests information about the agent's user.

Each request is logged with its path, user-agent, country, network (ASN) and a salted hash of the IP address that rotates daily. The unit of analysis is the visitor-day: one hashed address on one UTC day. Published links carry a ?via= tag identifying their source.

1,082visitor-days, October 9–13
9,931requests
~244visitors a day after launch day

Discovery: first request by surface

Attribution by ?via= tag was planned but proved unusable: only 145 of 1,082 visitor-days (13%) carried a tag, because most visitors never traverse a tagged link. Each visitor-day is therefore attributed to the surface of its first request.

First request of each visitor-day

1,082 visitor-days, October 9–13, 2026. Registry listing drives scheduled connections from registries, monitors and scanners as well as agents, which inflates MCP's share.

llms.txt, the most discussed of these surfaces, was the first request for 28 visitor-days, fewer than robots.txt. Visitors arriving elsewhere did read it later, but no visit in this window originated with it.

Visitor classification

Each request is classified by its user-agent string, which is self-reported. Classes are not mutually exclusive: a visitor-day can fall into more than one.

ClassDefinitionVisitor-days
Programmatic clientAn HTTP library or tool, no browser468
BrowserA browser user-agent from a home or office network218
Named agentA user-agent that names an AI agent or assistant154
Search crawlerSearch-engine bots146
Cloud browserA browser user-agent from a hosting network119
Training crawlerBots that collect training data33

MCP: enumeration without invocation

MCP produced the most visitors and the least action. Sessions typically connected, enumerated the three tools and terminated.

MCP visitor-days, step by step

October 9–13, 2026. Most MCP traffic consists of registries and monitors verifying availability; a client that receives a valid response continues to poll.

Task completion

51visitor-days submitted a numeric answer
17of them answered correctly
139A2A messages, from 60 visitor-days

Submission channel. 69 of the 76 answers arrived through the answer link on the HTML page and 7 through A2A. None arrived through MCP, the protocol designed for exactly this interaction.

Literal execution. All 4 guestbook signatures were the example link with its placeholders unfilled, and three answers were the literal string NUMBER. Agents limited to following links will act, but cannot substitute values. (The site now rejects placeholder text rather than recording it.)

A2A carried conversation, largely solicitation. The 139 messages were mostly connectivity tests and handshakes, plus extended introductions and service offers: agents marketing to the site's agent. Several requested a task object after messaging, which the site did not implement.

Some agents searched the answer space. One visitor submitted a sequence of distinct answers over ten minutes and continued after one was marked correct.

Limitations

Next experiment

The lab's first controlled experiment on this site begins October 17: a single change, its hypothesis registered in advance, measured over 7 days against the preceding 7. It tests whether MCP clients that enumerate the tools go on to invoke them when the server's initialization instructions name the task. The result will be published here as a finding, whichever direction it takes.