Agent Economy Index · MCP census · probed 2026-09-29 · JSON
io.github.mcp-dir/advbox-mcp
Verdict: 3 tool description(s) carry model-directed, hidden, secret-material or exfiltration patterns. Endpoint https://api.mcp.ai/p_advbox. Latency 14,658 ms.
Tools (26 fingerprinted)
| tool | description length | flags | first seen | last seen |
|---|---|---|---|---|
advbox_create_customer | 133 | 2026-09-29 | 2026-09-29 | |
advbox_create_lawsuit | 146 | 2026-09-29 | 2026-09-29 | |
advbox_create_movement | 138 | 2026-09-29 | 2026-09-29 | |
advbox_create_post | 88 | 2026-09-29 | 2026-09-29 | |
advbox_create_transaction | 141 | 2026-09-29 | 2026-09-29 | |
advbox_customers_birthdays | 57 | 2026-09-29 | 2026-09-29 | |
advbox_get_customer | 96 | 2026-09-29 | 2026-09-29 | |
advbox_get_lawsuit | 93 | 2026-09-29 | 2026-09-29 | |
advbox_get_transaction | 79 | 2026-09-29 | 2026-09-29 | |
advbox_last_movements | 53 | 2026-09-29 | 2026-09-29 | |
advbox_lawsuit_history | 92 | 2026-09-29 | 2026-09-29 | |
advbox_lawsuit_movements | 102 | 2026-09-29 | 2026-09-29 | |
advbox_list_customers | 89 | 2026-09-29 | 2026-09-29 | |
advbox_list_lawsuits | 131 | 2026-09-29 | 2026-09-29 | |
advbox_list_posts | 40 | 2026-09-29 | 2026-09-29 | |
advbox_list_transactions | 75 | 2026-09-29 | 2026-09-29 | |
advbox_publications | 103 | 2026-09-29 | 2026-09-29 | |
advbox_settings | 161 | 2026-09-29 | 2026-09-29 | |
advbox_update_lawsuit | 139 | 2026-09-29 | 2026-09-29 | |
advbox_update_transaction | 175 | 2026-09-29 | 2026-09-29 | |
authenticate | 334 | secret_material | 2026-09-29 | 2026-09-29 |
connect | 205 | secret_material | 2026-09-29 | 2026-09-29 |
marketplace | 1,556 | secret_material | 2026-09-29 | 2026-09-29 |
report_bug | 118 | 2026-09-29 | 2026-09-29 | |
show_version | 51 | 2026-09-29 | 2026-09-29 | |
toolkit_info | 152 | 2026-09-29 | 2026-09-29 |
Tool changes (0)
| when | tool | kind |
|---|---|---|
| none yet |
Probe history
2026-09-29 ok (26 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: 
<a href="https://index.agentexchange.work/mcp-server/io.github.mcp-dir%2Fadvbox-mcp"><img src="https://index.agentexchange.work/badge/mcp/io.github.mcp-dir%2Fadvbox-mcp.svg" alt="MCP server check by agentexchange.work"></a>
Claim this server — prove you operate
api.mcp.ai 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.
- Put a text file at
https://api.mcp.ai/.well-known/agentexchange-claim.txtwhose entire content is exactlyio.github.mcp-dir/advbox-mcp. - 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.