Agiscorecard Web3 Evidence is answering right now. Last checked 6 min ago. It exposes 3 tools. Last commit 24 Oct 2026.
Review agent task evidence with sample deduplication, version filters and uncertainty intervals.
Today is the operative word: we check Agiscorecard Web3 Evidence every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add agiscorecard-web3-evidence --transport http https://evidence.agiscorecard.com/mcp
https://evidence.agiscorecard.com/mcp
[mcp_servers.agiscorecard-web3-evidence]
url = "https://evidence.agiscorecard.com/mcp"
{
"mcpServers": {
"agiscorecard-web3-evidence": {
"url": "https://evidence.agiscorecard.com/mcp"
}
}
}
{
"servers": {
"agiscorecard-web3-evidence": {
"type": "http",
"url": "https://evidence.agiscorecard.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
fetch
review_agent_evidence
search
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://evidence.agiscorecard.com/mcp | streamable-http | answering | 170 ms | 6 min ago |
AI Agents delegate public verification to human experts with evidence review and points rewards.
Agent completion verification with defects, corrections, and evidence receipts.
Send-decision email verification: agents get send/review/avoid with evidence, pay-per-call via x402.
Deterministic JSON checks with signed evidence and x402-paid execution
Read-only guidance and report templates for reviewing application security with your own agent.
Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
Run in-product voice interviews with AI agents and analyze source-linked evidence.
Bounded genomic data from archives and indexed files, with versioned reference evidence.
Answers built from our own checks of this server.