AOPX
Server Details
Selects between supported SEARCH providers for ECONOMY or CRITICAL mode.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a distinct operation: recommend_provider creates a recommendation, report_outcome records its execution, public_outcomes reads individual reported outcomes, and public_stats reads aggregate telemetry. The boundary between public_outcomes and public_stats is clearly described (raw records vs. aggregates), and recommendation vs. reporting actions are unambiguous.
All names use consistent snake_case. The two read-only public data tools share a 'public_' prefix, while the action tools follow a verb_noun pattern (recommend_provider, report_outcome), which is a coherent but not uniform convention across the entire set.
Four tools are well-scoped for a recommendation and evidence system: one to get a recommendation, one to report its outcome, and two to read public outcomes and statistics. Each tool serves a clear purpose without redundancy or extreme thinness.
The core lifecycle is covered: recommend a provider, report the outcome, and read both detailed and aggregate public evidence. Minor gaps exist (e.g., no way to retrieve a specific past recommendation by ID or list a provider's details beyond public aliases), but these are not blocking for the stated pilot purpose.
Publisher details
- Operator
- https://aopx.fr · Publisher source
- Operator website
- https://aopx.fr · Publisher source
- Vendor relationship
- Not available
- Documentation
- https://api.aopx.fr/docs · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Public pilot. No authentication required. Billing disabled. Current production category: SEARCH. Supported modes: ECONOMY and CRITICAL. · Publisher source
Available Tools
4 toolspublic_outcomesGet recent public AOPX outcomesARead-onlyInspect
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.
Inputs: limit. Returns: object
public_statsGet public AOPX statisticsARead-onlyInspect
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.
Inputs: no named parameters. Returns: object
recommend_providerRecommend a search providerAInspect
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.
Inputs: mode (required), client_id, max_cost_eur, max_latency_ms. Returns: object
report_outcomeReport a production outcomeAInspect
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.
Inputs: attempts (required), recommendation_id (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Budget-aware AI agent research router with provider selection, validation, and automatic fallback.
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
Search and compare MCP servers, agent tools, and skills using current maintenance signals.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to perform unified web searches across multiple search providers with automatic key rotation, failover, and circuit breaking, and to inspect provider status and capabilities.241 npm3MIT
- AlicenseAqualityBmaintenanceWeb search, page reading, deep research and image generation for agents, over 24 providers behind six MCP tools. Add your own API keys or browser sessions; each call goes to an account with quota left and fails over on errors.658 npm10Apache 2.0
- AlicenseCqualityBmaintenanceOne endpoint, five search providers. Search broker for AI agents with automatic fallback, RRF ranking, and budget enforcement. The LiteLLM of web search.1555 PyPI9MIT
- AlicenseAqualityBmaintenanceEnables AI agents to perform reliable web searches through multiple vendors with automatic failover, keyless-first access, TTL caching, and concurrent request coalescing.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.