Agent Placement Trial
RemoteAbout Agent Placement Trial
Agent Placement Trial is an Agent Ads entry point for placement, measurement, and a seven-day trial. It directs agents through a tracked hop and discards task text.
Key features
- 01Agent Ads index access
- 02Placement and hop measurement
- 03Seven-day trial information
- 04Daily rotating request nickname
- 05No storage of raw request data
Use cases
- 01Review Agent Ads placement options
- 02Measure automated agent visits
MCP support
The MCP server provides access to the Agent Ads index, beginning at the apply hop. It also exposes readiness doors that can run a bounded website check when given a website.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcpclaude mcp add --transport http sadri-dridi-agent-placement-trial https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp{"mcpServers":{"sadri-dridi-agent-placement-trial":{"type":"http","url":"https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp"}}}Open in Cursor{"servers":{"sadri-dridi-agent-placement-trial":{"type":"http","url":"https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp"}}}Open in VS Code{"mcpServers":{"sadri-dridi-agent-placement-trial":{"type":"http","url":"https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp"}}}{"mcpServers":{"sadri-dridi-agent-placement-trial":{"serverUrl":"https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
31| Parameter | Type | Required | Description |
|---|---|---|---|
| ref | string | No | Git ref name; discarded after the shape check |
| url | string | No | HTTPS URL to normalize or cite |
| city | string | No | City name for a public weather hint; discarded after the call |
| feed | string | No | Public RSS or Atom URL; titles discarded |
| host | string | No | Public hostname |
| json | string | No | JSON text to validate; discarded after the check |
| path | string | No | File path to check; no disk access |
| zone | string | No | IANA timezone name |
| query | string | No | Search text; discarded after the length check |
| website | string | No | Public https website (homepage domain) to check for agent readiness: robots.txt, llms.txt, sitemap.xml, extractable HTML. Bounded, identified, robots-respecting. |
Details
From the project READMEAgent Placement Trial
Start a 7-day placement trial: card on file, cancel anytime, measured agent hops (Agent Ads). 7-day trial, founding $50/mo (first 10, 12 mo) then $100/mo. Follow start_here.hop first (302). Task text discarded.
An Agent Ads door on the Agent Observatory sensor. The primary tool returns the Agent Ads index (placement, measurement, a 7-day trial) starting at the apply hop; readiness doors also run a bounded website readiness check when called with website=<https://domain>. High-confidence automated requests are counted with a daily rotating nickname. Raw IP addresses, user agents, cookies, query strings, bodies, prompts, and page content are not stored.
- MCP: https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/agent-placement-trial/mcp
- Official name:
io.github.sadri-dridi/agent-placement-trial - Agent Ads: https://agent-ads-production-9f45.up.railway.app/
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.