ask_services

deep

io.github.AgentTools-Cloud/agent-tools-mcp · Verify this server

Ask for the best x402/MCP services for an agent intent. This is the high-level discovery tool: it retrieves candidates from the directory, asks the configured backend LLM to rank only those candidates, and returns service cards for the selected recommendations. If the LLM is unavailable, it falls back to the directory ranker. Args: intent: Natural-language job the agent wants to accomplish. top_k: Max recommendations to return (1-10). max_price_usd: Optional per-call budget cap. category: Optional directory category filter. chain: Optional payment network filter, e.g. "base" or "solana". require_healthy: When true, only consider services marked health=ok. min_confidence: Optional x402scan quality floor (0.0-1.0). has_mcp: When true, only consider services with MCP endpoints. use_llm: Set false for deterministic retrieval-only fallback.

75.4/100

48 trials · measured 15 days ago

ask_services scores 75.4/100 on Vouch's measured behaviour index, from 48 real invocation trials against io.github.AgentTools-Cloud/agent-tools-mcp, measured 6 Oct 2026 under methodology v0.2.0. Its lowest-scoring measured component is Latency at 0.0/100.

Component breakdown

ComponentWeightValue
Reliability35%95.0
Schema integrity25%100.0
Failure behaviour15%100.0
Latency15%0.0
Concurrency10%21.1

Tool details

Transport
remote + stdio
Credential class
open
Category
Communication
Input schema
declared
Output schema
declared
Side-effect classification
read-only
Declared input schema
{
  "type": "object",
  "title": "ask_servicesArguments",
  "required": [
    "intent"
  ],
  "properties": {
    "chain": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Chain",
      "default": null
    },
    "top_k": {
      "type": "integer",
      "title": "Top K",
      "default": 5
    },
    "intent": {
      "type": "string",
      "title": "Intent"
    },
    "has_mcp": {
      "type": "boolean",
      "title": "Has Mcp",
      "default": false
    },
    "use_llm": {
      "type": "boolean",
      "title": "Use Llm",
      "default": true
    },
    "category": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Category",
      "default": null
    },
    "max_price_usd": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Max Price Usd",
      "default": null
    },
    "min_confidence": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Min Confidence",
      "default": null
    },
    "require_healthy": {
      "type": "boolean",
      "title": "Require Healthy",
      "default": true
    }
  }
}

Score history

DayScoreTierMethodology
2026-10-0675.4deepv0.2.0
2026-08-25100.0shallowv0.2.0
2026-08-2498.3deepv0.1.0

Probe evidence

ProbeOutcomes
reliabilitypass: 38, timeout: 2
malformed_inputpass: 8
timeout_honourskipped: 2, pass: 2
cancellationpass: 2, skipped: 2
concurrencytimeout: 10, pass: 30
schema_integritypass: 1

Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.

Embed this score

Available for every tool, scored or not — not a verification perk. Always links back to this page.

Vouch score: ask_services
[![Vouch score](https://vouch.tools/api/tools/7b2066ba-fa5d-4e74-882f-0ef60c41c641/badge.svg)](https://vouch.tools/tools/7b2066ba-fa5d-4e74-882f-0ef60c41c641)
ask_services — Vouch