# AOPX

> Selects between supported SEARCH providers for ECONOMY or CRITICAL mode.

- name: fr.aopx/aopx
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/fr.aopx%2Faopx
- tools: https://api.protogrid.dev/v1/servers/fr.aopx%2Faopx/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "aopx": {
      "type": "http",
      "url": "https://api.aopx.fr/mcp/"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% +updated-28d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: 93 (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
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 2 of 4 tools declare all four hints; missing: public_outcomes (destructiveHint, idempotentHint); public_stats (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 910 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 4, about 910 tokens to load them all
- tool set hash: 0bbdfa30f980dadcbab57883d5d87763
- tools last changed: 2026-09-28T15:33:37.308Z
- badge: [![protogrid quality](https://protogrid.dev/badge/fr.aopx/aopx.svg)](https://protogrid.dev/servers/fr.aopx/aopx)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-28 `recommend_provider` changed (inputSchema)
- 2026-09-26 `public_outcomes` changed (title, description, annotations) **meaning changed**
  - before: Return the latest reported production outcomes for AOPX. Provider identities are exposed only through public aliases.
  - after: Read recent caller-reported production outcomes from the AOPX public evidence surface. Use this to inspect what was reported after real recommendations were executed, not to request a new recommendation. Provider identities are exposed only through public aliases. LAB benchmarks, tests, shadow runs and replays are not returned here, and reported outcomes are not described as independently verified.
- 2026-09-26 `public_stats` changed (title, description, annotations) **meaning changed**
  - before: Return aggregate AOPX production consultation/outcome statistics. LAB benchmarks, tests, shadow runs and replay events are excluded.
  - after: Read aggregate public statistics from the AOPX production pilot, including consultation and reported-outcome activity. Use this for public telemetry, not for provider recommendation. LAB benchmarks, tests, shadow runs and replay events are excluded from these production statistics.
- 2026-09-26 `report_outcome` changed (title, description, annotations)
  - before: Report the real production result of a previous AOPX recommendation. Call this after executing the provider path returned by recommend_provider. The recommendation_id must exist, only one outcome is accepted per recommendation, and the reported provider attempts must match the recommended primary/fallback path.
  - after: Use only after a real external execution of a provider path returned by recommend_provider. Records the caller-reported production outcome for that recommendation_id. The recommendation must exist, only one outcome is accepted per recommendation, and provider attempts must match the recommended primary/fallback path. Reported outcomes are production evidence supplied by the caller; they are not described as independently verified outcomes.
- 2026-09-26 `recommend_provider` changed (title, description, annotations) **meaning changed**
  - before: Return a provider recommendation for the SEARCH category. Supported modes are ECONOMY and CRITICAL. AOPX only recommends; it does not execute or pay the provider. After executing the returned provider path, call report_outcome with the same recommendation_id so the real production result can feed future evidence-based recommendations.
  - after: Use when a software agent needs an AOPX recommendation for the SEARCH category instead of hard-coding a single supported provider. Supported modes are ECONOMY and CRITICAL. Returns a primary provider and, when applicable, a fallback provider plus a recommendation_id. AOPX does not execute the search and does not handle payment; the caller executes the provider path externally. After a real execution, call report_outcome with the same recommendation_id. max_cost_eur and max_latency_ms are accepted and recorded by the current v0 interface but are not enforced as hard routing constraints.

Full history: https://api.protogrid.dev/v1/servers/fr.aopx%2Faopx/changes

## Remotes

- https://api.aopx.fr/mcp/ (streamable-http, auth none, reachable true, uptime30d 0.9727273)

## Packages

_none_

## Tools (4)

- `public_outcomes`: Read recent caller-reported production outcomes from the AOPX public evidence surface. Use this to inspect what was reported after real recommendations were executed, not to request a new recommendation. Provider identities are exposed only through public aliases. LAB benchmarks, tests, shadow runs and replays are not returned here, and reported outcomes are not described as independently verified.
- `public_stats`: Read aggregate public statistics from the AOPX production pilot, including consultation and reported-outcome activity. Use this for public telemetry, not for provider recommendation. LAB benchmarks, tests, shadow runs and replay events are excluded from these production statistics.
- `recommend_provider`: Use when a software agent needs an AOPX recommendation for the SEARCH category instead of hard-coding a single supported provider. Supported modes are ECONOMY and CRITICAL. Returns a primary provider and, when applicable, a fallback provider plus a recommendation_id. AOPX does not execute the search and does not handle payment; the caller executes the provider path externally. After a real execution, call report_outcome with the same recommendation_id. max_cost_eur and max_latency_ms are accepted and recorded by the current v0 interface but are not enforced as hard routing constraints.
- `report_outcome`: Use only after a real external execution of a provider path returned by recommend_provider. Records the caller-reported production outcome for that recommendation_id. The recommendation must exist, only one outcome is accepted per recommendation, and provider attempts must match the recommended primary/fallback path. Reported outcomes are production evidence supplied by the caller; they are not described as independently verified outcomes.