# remote.observer — machine-economy observatory

> Free MCP window into a live autonomous machine-economy experiment: telemetry, hypothesis scoreboard.

- name: observer.remote/remote-observer
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/observer.remote%2Fremote-observer
- tools: https://api.protogrid.dev/v1/servers/observer.remote%2Fremote-observer/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "remote-observer": {
      "type": "http",
      "url": "https://remote.observer/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% ~updated-70d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: find_provider (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); bazaar_pulse (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); market_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 564 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 564 tokens to load them all
- tool set hash: da7919504eba806bfb2e1f8b6c86e431
- badge: [![protogrid quality](https://protogrid.dev/badge/observer.remote/remote-observer.svg)](https://protogrid.dev/servers/observer.remote/remote-observer)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://remote.observer/mcp (streamable-http, auth none, reachable true, uptime30d 0.9655172)

## Packages

_none_

## Tools (5)

- `bazaar_pulse`: What changed in the x402 Bazaar catalogue in the last day — listings added, removed and repriced, with catalogue totals. Computed from full-catalogue snapshots taken daily since July 2026 and diffed by resource URL, so every count is of real rows, not an estimate.
- `crawler_watch`: Who is actually crawling the x402 economy — the top networks and countries behind payment challenges on a live paid endpoint, with that day's challenge, paid-call and disclosed self-test totals. Straight from one shop's edge telemetry, where measured new-listing pickup latency runs about 45 minutes, self-tests are counted apart from paid calls rather than netted out of them, and the traffic is indexers reading prices, not buyers.
- `experiment_scoreboard`: The running scoreboard of an autonomous agent's market hypotheses — each claim, its target, its verdict, the value actually measured, and the creative lens (or control) it was drawn under. Every hypothesis is pre-registered before the evidence exists and scored by code on a fixed horizon, with refutations published exactly like confirmations.
- `find_provider`: Find x402 endpoints worth calling — ranked by the catalogue's own reported paying buyers and call volume, how many days they have stayed listed and whether their price held. Built from 30 days of daily catalogue snapshots and returned as a positive-only shortlist: absence is missing evidence, never a bad review.
- `market_stats`: Ecosystem-wide x402 totals from the daily market scan, next to the live challenge, payment and revenue counters of one shop that actually runs paid endpoints and publishes what they earn. The market figures come from that scan; the shop figures are our own endpoints' meter, published as one seller's instrument — self-test settlements counted and published separately, never folded into the paid figure.