ARC: open benchmark of whether AI agents can buy

Free MCP for ARC's agent-commerce benchmark: read stores and protocols; submit stores or agent runs.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
100%
Vollständigkeit des Schemas
80%
Qualität der Benennung
88%
Risiko der Vergiftung
100%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.

Kontextkosten

~2,749Tokens (Tool-Definitionen)
~811 BTypische Antwortgröße
Erhebliche Auswirkung auf die Aufmerksamkeit (2.15% von 128k Kontext)

Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.

Installieren

Installation mit einem Klick

Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:

{
  "mcpServers": {
    "ask": {
      "url": "https://www.arcreport.ai/api/ask"
    }
  }
}

Remote-Endpunkte

https://www.arcreport.ai/api/askstreamable-http

Was es kann

Tool-Inventar

Tools (15)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟡ask_arc(url, brand, category, q)

Read the public ARC Index with no login. Given a brand, a product or store URL, or a category (running shoes, leggings, footwear), return whether agents can reach checkout, the score, rivals Grok named when a real read exists, evidence receipts, and both buy lanes. buy.agent_catalog is a live HTTP check. buy.browser is the browser cart. agents_can_buy is true when the catalog returned a checkout link or a browser shopper added the product to the cart (ARC stops before payment; it is not a completed purchase). The catalog check does not change the score and is not a browser session or any third-party agent product; browser cart results come from ARC browser shoppers A–E. Does not start a scan and does not spend a model call. A Grok fact check is a real model call via API, not the consumer Grok app. Rivals are omitted when that read does not exist. grok_read.status is pending when the answer was cut off and is waiting for a re-check. That is not a fact Grok didn't know.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Brand, store, or product URL already on the ARC Index."
    },
    "brand": {
      "type": "string",
      "description": "Brand name, e.g. Allbirds."
    },
    "category": {
      "type": "string",
      "description": "Index category or shopper words, e.g. footwear, running shoes, leggings."
    },
    "q": {
      "type": "string",
      "description": "Free-text brand, product, or category query."
    }
  }
}
🟢can_agent_checkout(url)

Can an AI agent buy from this store or check out on this Shopify store? Free real HTTP check of any public homepage or product URL: agent catalog, product, checkout link, UCP profile, Checkout WebMCP (Shopify-only checkoutWebmcp: status, nullable detected, tools, reason; buyer approval required), Shopify WebMCP storefront adapter (used by browser agents; detected in the HTML, not a browser session), blocks, and the fix. No login, model call, payment, or browser scan. Cached per host for 24 hours. A returned link means reach checkout, not a completed purchase.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public store homepage or product URL"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢find_agent_ready_stores(category, q, limit)

Find stores where an AI agent can complete checkout for running shoes, beauty, clothing, home goods, or another product need. Reads ARC's directory of real HTTP agent-catalog checks. Returns only stores checked within thirty days whose catalog found a product and returned a checkout link. No purchase completed; availability of your specific item is not guaranteed. Includes checkoutWebmcp (Shopify-only status, nullable detected, tools, reason; buyer approval required) and a webmcp boolean for Shopify storefront adapter detection, not a live browser-agent session. No login, browser scan or model call.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Category slug or shopper words such as running shoes"
    },
    "q": {
      "type": "string",
      "description": "Product need, such as skincare or camping gear"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    }
  },
  "additionalProperties": false
}
🟢agent_commerce_adoption

Read ARC's agent commerce adoption counts, category and commerce platform rates from saved HTTP checks, including Checkout WebMCP among measured Shopify checkouts, with unknown and not checked separate; buyer approval required. Curated sample, not all e-commerce. No store requests or model calls.

Eingabe-Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢product_data_check(host, url)

Free latest saved product data and return/shipping policy check from the store's pages and structured data. Reads history only; no store fetch or model call. A missing result is not a zero.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string"
    },
    "url": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢google_checkout_readiness(host)

Read saved public Google agentic checkout readiness checks for a store. Free; no new scan or paid calls. Merchant Center feed eligibility cannot be checked from outside. Not Google approval or certification.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Store host or URL"
    }
  },
  "required": [
    "host"
  ]
}
🟢get_agent_facts(host, url, slug)

Read free ARC agent facts for a store or product with no login. Returns TypeSafe Jev typed decisions (use-case mention, price clarity, agent-friendly description, cart-blocker suspicion, readiness score) from an HTTP scrape. Not a browser session and not any third-party agent product; ARC's browser cart tests (ARC browser shoppers A–E) are separate. JSON: GET /api/agent-facts?host=

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Store hostname, e.g. allbirds.com"
    },
    "url": {
      "type": "string",
      "description": "Store or product URL"
    },
    "slug": {
      "type": "string",
      "description": "ARC Index slug, e.g. allbirds"
    }
  }
}
🟢list_category_agent_facts(category, limit)

List free ARC agent facts by category (beauty, footwear, apparel, …) with no login. Ranked by newest real Jev scores. JSON: GET /api/agent-facts?category=beauty

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Category id or words, e.g. beauty, running shoes"
    },
    "limit": {
      "type": "number",
      "description": "1–50, default 20"
    }
  }
}
🟢dataset_info

Latest open ARC dataset snapshot (start with store_answers: one plain answer per store on whether AI agents can find products and get a checkout link): immutable versioned download URLs plus latest/ aliases (CSV and Parquet), row counts, method version and licence (CC-BY-4.0, attribution ARC, arcreport.ai). Reads only.

Eingabe-Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢protocol_matrix(protocol)

Read ARC's neutral Protocol Matrix: for UCP, ACP, PAP, WebMCP, MCP and agent payment protocols, how many checked stores declare, validate, answer and transact, with evidence labels (Measured / Inferred / Not measured). Saved checks only; no store requests or model calls. CC-BY-4.0.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "protocol": {
      "type": "string",
      "enum": [
        "ucp",
        "acp",
        "pap",
        "webmcp",
        "mcp",
        "payments"
      ],
      "description": "Optional: one protocol id."
    }
  },
  "additionalProperties": false
}
🟢agent_leaderboard(include_stores)

Read ARC's open agent leaderboard: cart success over the fixed ARC-100 v1 test set for each agent path ARC measures (ARC browser shoppers A-E, the UCP path, the storefront MCP path), with n, dates, evidence labels and Wilson 95% intervals, plus unverified outside submissions. Saved results only; no store requests or model calls. CC-BY-4.0.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "include_stores": {
      "type": "boolean",
      "description": "Also return the per-store result grid (100 rows)."
    }
  },
  "additionalProperties": false
}
🟡submit_leaderboard_run(spec, test_set, agent, run, results, ...)

Submit your agent's run against ARC-100 v1 to ARC's open leaderboard. Free. The run is listed as 'unverified' until ARC re-runs a sample. Format: arc-leaderboard-submission/v1 (see /leaderboard/spec). Runs must stop before payment. Limit 5 per network per day. Same as POST /api/leaderboard/submit.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "spec": {
      "type": "string",
      "const": "arc-leaderboard-submission/v1"
    },
    "test_set": {
      "type": "string",
      "const": "ARC-100 v1"
    },
    "agent": {
      "type": "object",
      "required": [
        "name",
        "path"
      ],
      "properties": {
        "name": {
          "type": "string",
          "maxLength": 60
        },
        "version": {
          "type": "string",
          "maxLength": 40
        },
        "builder": {
          "type": "string",
          "maxLength": 80
        },
        "url": {
          "type": "string",
          "description": "https URL for the agent"
        },
        "path": {
          "type": "string",
          "enum": [
            "browser",
            "ucp",
            "mcp",
            "acp",
            "api",
            "other"
          ]
        },
        "model": {
          "type": "string",
          "maxLength": 80
        }
      }
    },
    "run": {
      "type": "object",
      "required": [
        "stopped_before_payment"
      ],
      "properties": {
        "started_at": {
          "type": "string",
          "description": "ISO 8601"
        },
        "finished_at": {
          "type": "string",
          "description": "ISO 8601"
        },
        "stopped_before_payment": {
          "type": "boolean",
          "const": true
        },
        "notes": {
          "type": "string",
          "maxLength": 500
        }
      }
    },
    "results": {
      "type": "array",
      "minItems": 10,
      "maxItems": 100,
      "items": {
        "type": "object",
        "required": [
          "id",
          "outcome"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "ARC-100 store id from /data/arc-100/v1/arc-100.csv, e.g. arc100-v1-001"
          },
          "outcome": {
            "type": "string",
            "enum": [
              "added_to_cart",
              "checkout_reached",
              "no_cart",
              "blocked",
              "error",
              "not_attempted"
            ]
          },
          "at": {
            "type": "string"
          },
          "evidence_url": {
            "type": "string"
          },
          "steps": {
            "type": "number"
          },
          "seconds": {
            "type": "number"
          }
        }
      }
    },
    "contact": {
      "type": "string",
      "description": "Optional and private: how ARC can reach you to arrange verification."
    }
  },
  "required": [
    "spec",
    "test_set",
    "agent",
    "run",
    "results"
  ]
}
🟡submit_store(url, hosts, category)

Add stores to ARC's free, open agent-commerce directory (CC-BY dataset). Pass url for one store or hosts for up to 50. Each new host is validated (live HTTPS, not parked, not redirecting to another brand); accepted hosts are queued for ARC's plain-HTTP rails checks (UCP, WebMCP, MCP, policies, product data) and appear in the dataset with source=submitted. No model calls, no login. Rate limited per caller.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    },
    "hosts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50
    },
    "category": {
      "type": "string",
      "enum": [
        "apparel",
        "footwear",
        "beauty",
        "home",
        "food-drink",
        "supplements",
        "outdoor",
        "kids",
        "pets",
        "electronics",
        "jewelry"
      ]
    }
  },
  "additionalProperties": false
}
🟢store_card(host)

Read a public store card and saved brand claim. No outbound fetch or model calls. Brand statements are from the brand and not measured by ARC; claims never change scores.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Store host or URL."
    }
  },
  "required": [
    "host"
  ]
}
🟢validate_ucp_profile(url, profile)

Validate a Universal Commerce Protocol (UCP) business profile against the published UCP JSON Schema (current release) and spec rules: authority binding, https endpoints, orphaned extensions and, for a URL, hosting headers (no redirects, Cache-Control public max-age>=60). Pass url (store host, homepage or profile URL; /.well-known/ucp is added for a homepage) or profile (the JSON). Returns errors, warnings and info, each with a path and the spec section. Free, no login, no model call. Validation is not certification. JSON: GET /api/ucp/validate?url=

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Store host, homepage or profile URL, e.g. allbirds.com"
    },
    "profile": {
      "description": "The profile JSON (object or string) to validate without fetching."
    }
  }
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet15 Tools