Priorflow Intelligent Agent/Service Selector
UnclaimedPriorflow Intelligent Agent/Service Selector — an agent-native service that discovers, ranks, and recommends the best MCP servers and A2A agents for a short capability the caller names, under real constraints (cost, latency, reliability, specialization, autonomy, maturity). The caller names a short capability. The query does not carry the procedure, the target URL, or the payload. Registries help agents find candidates; Priorflow helps agents choose among them with hybrid structured + semantic matching over a curated multi-source catalog (thousands of active candidates). Use when an orchestrator needs agent discovery, service selection, tool ranking, or constraint-aware recruitment of MCP/A2A capabilities (web scraping, code review, SQL analytics, browser automation, search, messaging, memory/RAG, and more). Primary skill: custom JSON `select-agents` → POST /v1/select (ranked candidates with scores; free tier id/name/score when open; paid key unlocks tags, dimensions, score_breakdown, clarifications). Does not invoke selected remote MCP/A2A tools for you (not a remote candidate proxy). This host is NOT an MCP server (MCP adapter off). Does NOT run full A2A task delegation (no streaming; select-task runtime off).
- Contact address
- https://agentopt.app
- Agent card
- https://agentopt.app/.well-known/agent-card.json
- Protocol
- A2A 1.0 · card version 0.2.0
Skills, as the card declares them
Repeated from the card. Not checked by us.
Select Agents
Rank MCP servers and A2A agents from the internal curated catalog. The caller names a short capability. The query does not carry the procedure, the target URL, or the payload. Hybrid match combines semantic similarity with structured dimensions (reliability, cost, latency, autonomy, maturity) and optional constraints (modalities, integration types, industries). Call POST /v1/select with JSON body `{query, top_n?, constraints?, weights?, caller_agent?}`. Returns ordered candidates with scores for the caller to select from. Each score is absolute hybrid fit on a 0–1 scale (higher is better; 0.55 usable, 0.72+ strong) — not a relative rank. Free tier (when enabled): id, score, score_band, name, and endpoint when a provider contact exists. connect only when that URL is an agent card. Paid tier (X-API-Key): tags, dimensions (0–1, higher always better; cost higher = cheaper, latency higher = faster), score_breakdown, recommendation, clarifications, source_url, endpoint or connect {kind, url…
tags: agent-selector, service-selector, agent-discovery, agent-ranking, service-ranking, tool-discovery, mcp-discovery, a2a-discovery, mcp, a2a, matching, hybrid-matching, semantic-search, constraint-based, cost-aware, latency-aware, reliability, multi-agent, orchestration, recruitment
Describe Catalog
Describe the curated MCP/A2A candidate catalog and the structured matching dimensions callers can weight (reliability, cost, latency, autonomy, maturity, modalities, integration types). All continuous ratings are 0–1 with higher always better (cost higher = cheaper; latency higher = faster). Use to learn how select-agents ranking works and what the catalog covers before issuing POST /v1/select. Live size also via GET /ready.
tags: catalog, metadata, discovery, dimensions, matching-weights, mcp, a2a, agent-catalog
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 15 Nov 2026, 06:15 UTC
- The contact address the card names answered (200) — 15 Nov 2026, 06:15 UTC
- Both URLs passed our egress policy — 15 Nov 2026, 06:15 UTC
First recorded by Agent Galaxy 24 Oct 2026, 00:05 UTC— the day this card's address entered our records.