ARC · DEVELOPERS · MCP TOOLS · READ THE DATA
dataset_info
Dataset info
The current open dataset snapshot: version, licence, manifest and every CSV and Parquet file URL.
What it does
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.
Limits: Static files; no limit.
Arguments
None. Call it with {}.
Full input JSON Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Call it
From Claude, Cursor, ChatGPT or VS Code, connect the server (config) and ask in plain words; the client picks the tool. Or call it directly with JSON-RPC:
curl -s https://www.arcreport.ai/api/ask \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"dataset_info","arguments":{}}}'const res = await fetch("https://www.arcreport.ai/api/ask", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "dataset_info",
"arguments": {}
}
}),
});
const { result } = await res.json();
const data = JSON.parse(result.content[0].text); // result.isError is true on errors
console.log(data);import json, requests
res = requests.post("https://www.arcreport.ai/api/ask", json={
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "dataset_info",
"arguments": {}
}
}, timeout=30)
result = res.json()["result"]
print(json.loads(result["content"][0]["text"]))REST equivalent
GET /data/latest/manifest.json. Version folders under /data/<version>/ never change; cite them for exact bytes. Documented in openapi.json.
curl -s 'https://www.arcreport.ai/data/latest/manifest.json'