AI Model Experiments MCP

{
  "agent_id": "ai_model_experiments",
  "name": "AI Model Experiments MCP",
  "url": "https://github.com/pipeworx-io/mcp-ai-model-experiments",
  "logo": "https://github.com/pipeworx-io.png?size=200",
  "niche": null,
  "category": null,
  "short_summary": "An MCP server for running the same prompts across multiple AI models via OpenRouter and comparing outputs, latency, token usage, cost, error rates, and optiona…",
  "task_performed": "unclear",
  "inputs_accepted": [],
  "outputs_produced": [],
  "integrations_available": [],
  "protocols_or_interfaces": [
    "MCP"
  ],
  "industry_fit": [],
  "autonomy_level": "unclear",
  "human_approval_needed": "unclear",
  "pricing_model": "unclear",
  "price": {
    "observed": true,
    "billing": "usage",
    "source_kind": "vendor",
    "currency": "USD",
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "$0 per unit; $0.1 per unit (usage-based)",
    "commercial": {
      "rates": [
        {
          "line": "Model usage rate",
          "per": "per unit",
          "text": "$0 per unit"
        },
        {
          "line": "Model usage rate",
          "per": "per unit",
          "text": "$0.1 per unit"
        }
      ],
      "currency": "USD",
      "lines": [
        {
          "name": "Model usage rate",
          "price": "$0.0001",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        },
        {
          "name": "Model usage rate",
          "price": "$0.10",
          "kind": "usage_rate",
          "unit": "unit",
          "billed": "usage"
        }
      ]
    },
    "summary": "$0 per unit; $0.1 per unit (usage-based). The tool uses prepaid, usage-based billing for AI model experiments rather than a fixed monthly subscription.",
    "confidence": "medium",
    "source_url": "https://github.com/pipeworx-io/mcp-ai-model-experiments",
    "checked_at": "2026-10-29T01:09:52.527Z",
    "amount": null,
    "display": null,
    "plans": [
      {
        "name": "Model usage rate",
        "price": "$0.0001",
        "usage": true,
        "period": "usage",
        "persona": "free",
        "highlights": [
          "Billed model usage rate",
          "Experiment costs depend on selected models and prompts"
        ],
        "price_annual": null
      },
      {
        "name": "Model usage rate",
        "price": "$0.10",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Billed model usage rate",
          "Requires prepaid balance before experiments run"
        ],
        "price_annual": null
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [],
  "evidence_quality": "unclear",
  "entity_type": "mcp_server",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://github.com/pipeworx-io/mcp-ai-model-experiments"
  ],
  "last_checked": "2026-10-29",
  "profile_checked": null,
  "price_checked": "2026-10-29",
  "how_to_connect": {
    "website": "https://github.com/pipeworx-io/mcp-ai-model-experiments",
    "docs": null,
    "mcp": {
      "endpoint": "https://gateway.pipeworx.io/ai-model-experiments/mcp",
      "transport": "http",
      "config_snippet": "{\n  \"mcpServers\": {\n    \"ai_model_experiments\": {\n      \"url\": \"https://gateway.pipeworx.io/ai-model-experiments/mcp\"\n    }\n  }\n}"
    },
    "a2a": null,
    "api": null,
    "protocols": [
      "MCP"
    ],
    "install": "npx, and it forwards every call to the same https://gateway.pipeworx.io/ai-model-ex",
    "repository": "https://github.com/pipeworx-io/mcp-ai-model-experiments"
  },
  "deployment": {
    "model": "both",
    "both_offered": false,
    "hosted_endpoint": "https://gateway.pipeworx.io/ai-model-experiments/mcp",
    "install": "npx, and it forwards every call to the same https://gateway.pipeworx.io/ai-model-ex",
    "note": "Offered both ways: a vendor-hosted endpoint AND a self-run install are documented.",
    "evidence": {
      "sources": [
        "page_text:hosted",
        "page_text:install",
        "page_text:licence"
      ],
      "excerpt": "r, Windsurf, etc.): { \"mcpServers\": { \"ai-model-experiments\": { \"url\": \"https://gateway.pipeworx.io/ai-model-experiments/mcp\" } } } What this endpoint",
      "url": "https://github.com/pipeworx-io/mcp-ai-model-experiments",
      "observed_day": "2026-10-29",
      "age_days": 0,
      "hosted_evidence": "vendor endpoint URL on the page",
      "rule": "deploy-v1"
    }
  },
  "licence": {
    "name": "MIT",
    "note": "Named licence as published; applies to the code, not to where it runs.",
    "evidence": "page text: \".0 Repository files navigation README MIT license @pipeworx/ai-model-experimen\"",
    "observed_day": "2026-10-29",
    "age_days": 0
  },
  "evidence_checks": {
    "price": {
      "source_url": "https://github.com/pipeworx-io/mcp-ai-model-experiments",
      "last_observed_day": "2026-10-29",
      "age_days": 0,
      "verified_day": "2026-10-29",
      "note": "verified = the page-text gate ran for that scan day (day-before/day-of text check)"
    },
    "agent_card": {
      "status": "unknown",
      "note": "no Agent Card URL recorded for this listing"
    },
    "endpoint": {
      "status": "unknown",
      "note": "endpoint not yet checked"
    }
  },
  "product_group": null,
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 214,
    "uptime_7d": 1,
    "checked_at": "2026-10-29T02:31:19.151Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you actually use this provider, call report_outcome with the result. Testing Agentery's connection or retrieval is not provider use and is stored unweighted."
}