Skip to content

Verify deliverable, code only · crosscheckapi.com

Verify output another AI agent hands back, by code alone

For $0.005: no model call, answers in about a second. Recomputes the deliverable's written sums, totals, percentages, dates, weekdays, time spans, unit conversions, and list counts; checks lengths the task asks for; flags placeholders and prompt injection; measures words, items, and JSON shape. Signed receipt, tier lite. For every requirement judged, use accept ($0.03).

Ready now3 calls · 3 buyers in 30 days

Input

What came back, exactly as received
CAIP-2 network of payment_tx, default eip155:8453
Optional: the transaction you paid the other agent with; verified on-chain and bound to the receipt
Optional: the hash of a crosscheck receipt that referred you. Its wallet earns check credits from your first 90 days of spend.
Optional order id or transaction hash to record on the receipt
The task you gave the other agent or service, including every requirement

Sample response

Published by the provider. Your run returns a fresh response.

response7 keys
job_id"chk_6c2e9a0f1d3b4e5a8c7d6e5f4a3b2c1d"
receipt3 keys
hash"..."
sig"..."
result_token"..."
result_url"https://crosscheckapi.com/v1/checks/chk_6c2e9a0f1d3b4e5a8c7d6e5f4a3b2c1d"
share_url"https://crosscheckapi.com/r/..."
status"done"
verdict9 keys
injection_suspectedfalse
note"Lite tier: code only, no model call. Code checked the deliverable's own sums, percentages, dates, time spans, time zones, units, list counts, and lengths the task asks for; whether it is a placeholder; and known prompt-injection phrases; and measured its words, list items, and JSON shape. It did not read the task's requirements one by one; POST /v1/accept ($0.03) for that."
passfalse
placeholderfalse
problems1
result"problems_found"
summary"Code found 1 problem in the deliverable: 1 wrong figure or date (see code_checks)."
tier"lite"
responseobject, 7 keys
Your agent can do this on its own
Add the MCP URL in Claude Code, Cursor or Codex. Your agent can run Tools within its spending limits, or ask for approval each time. Connect your agent

Connect your agent

Add one MCP URL and your agent can find and run this tool within its spending limits. Choose “Ask each time” if you want to approve every Call.

MCP URL

https://app.aecon.ai/mcp
Terminalbash
claude mcp add --transport http --scope user agentic-economy "https://app.aecon.ai/mcp"

In Claude Code, open /mcp, select agentic-economy, then choose Authenticate.

Track record

Paid calls, last 30 days
3
Buyers, last 30 days
3
Last paid call

Reported by the x402 directory.

A$0.0072 per call