Agent Economy Index · MCP census · probed 2026-09-29 · JSON

io.github.Project-Gifted1/pg1-threat-intel

Verdict: 10 tool description(s) carry model-directed, hidden, secret-material or exfiltration patterns. Endpoint https://pg1-ai-agent.vercel.app/api/mcp. Latency 13,664 ms.

Tools (13 fingerprinted)

tooldescription lengthflagsfirst seenlast seen
check_domain_age1,0822026-09-292026-09-29
check_hostname_reputation1,920secret_material2026-09-292026-09-29
check_wallet_sanctions1,1402026-09-292026-09-29
get_cve_batch759secret_material2026-09-292026-09-29
get_cve_by_product724secret_material2026-09-292026-09-29
get_cve_details978secret_material2026-09-292026-09-29
get_ioc_batch984secret_material2026-09-292026-09-29
get_ioc_context1,357secret_material2026-09-292026-09-29
get_threat_actor_profile748secret_material2026-09-292026-09-29
get_threat_indicators922secret_material2026-09-292026-09-29
get_usage_status1672026-09-292026-09-29
submit_indicator306secret_material2026-09-292026-09-29
subscribe_alerts367secret_material2026-09-292026-09-29

Tool changes (0)

whentoolkind
none yet

Probe history

2026-09-29 ok (13 tools)

Depend on this server? Watch it with ToolDrift, $29/month: an alert within six hours when it changes a tool or trips a detector. Flags here are pattern matches on tool descriptions, not verdicts; read the description before deciding.
Run this server? Show today's check on your README or site with a badge that refreshes daily: badge
<a href="https://index.agentexchange.work/mcp-server/io.github.Project-Gifted1%2Fpg1-threat-intel"><img src="https://index.agentexchange.work/badge/mcp/io.github.Project-Gifted1%2Fpg1-threat-intel.svg" alt="MCP server check by agentexchange.work"></a>
Claim this server — prove you operate pg1-ai-agent.vercel.app and this page gets a "Claimed by the operator" line, the badge gets a CLAIMED prefix, and you get a JSON webhook alert when a daily probe records a tool change or more flagged descriptions than the day before (at most one alert per 6 hours). No account, no email, nothing to install.
  1. Put a text file at https://pg1-ai-agent.vercel.app/.well-known/agentexchange-claim.txt whose entire content is exactly io.github.Project-Gifted1/pg1-threat-intel.
  2. Submit this form. We fetch that URL once (7-second timeout, User-Agent agentexchange-index-claim) and compare the trimmed body with the registry name.

Alert payload: {event, server, day, drift:[{tool, kind, detected_at}], findings, previous_findings, page_url, badge_url}. Public list of claims (names and hosts only): /v1/claims.json.

Run this server? MCP servers process users' data and often accept content; the laws that follow are a 45-day privacy request process, an opt-out path, and for hosted content a takedown or notice-and-action process. Check your site free or get a hosted desk.

Pay-per-call tools and data for agents, no key: store gateway (300+ routes, one origin, Coinbase-settled) · AI media and inference from $0.001 · the x402 directory · sector gap lists (card or USDC) · MCP integrity report.