Agent Economy Index · MCP census · probed 2026-09-29 · JSON
io.github.YS-projectcalc/agent-cold-email
Verdict: 2 tool description(s) carry model-directed, hidden, secret-material or exfiltration patterns. Endpoint https://api.coldrig.dev/mcp. Latency 5,530 ms.
Tools (28 fingerprinted)
| tool | description length | flags | first seen | last seen |
|---|---|---|---|---|
account | 865 | 2026-09-29 | 2026-09-29 | |
ack_message | 420 | 2026-09-29 | 2026-09-29 | |
activity | 327 | 2026-09-29 | 2026-09-29 | |
campaign_results | 322 | 2026-09-29 | 2026-09-29 | |
configure_byo_domain | 1,208 | 2026-09-29 | 2026-09-29 | |
configure_dashboard | 317 | 2026-09-29 | 2026-09-29 | |
configure_webhook | 497 | 2026-09-29 | 2026-09-29 | |
contact_operator | 1,644 | 2026-09-29 | 2026-09-29 | |
get_byo_domains | 448 | 2026-09-29 | 2026-09-29 | |
get_dashboard | 269 | 2026-09-29 | 2026-09-29 | |
get_webhooks | 341 | 2026-09-29 | 2026-09-29 | |
inbox | 341 | 2026-09-29 | 2026-09-29 | |
infrastructure_status | 3,134 | secret_material | 2026-09-29 | 2026-09-29 |
label_thread | 278 | 2026-09-29 | 2026-09-29 | |
launch_campaign | 3,469 | 2026-09-29 | 2026-09-29 | |
list_campaigns | 255 | 2026-09-29 | 2026-09-29 | |
list_leads | 510 | 2026-09-29 | 2026-09-29 | |
list_messages | 1,276 | secret_material | 2026-09-29 | 2026-09-29 |
mark | 330 | 2026-09-29 | 2026-09-29 | |
metrics | 313 | 2026-09-29 | 2026-09-29 | |
pause | 258 | 2026-09-29 | 2026-09-29 | |
pause_all | 209 | 2026-09-29 | 2026-09-29 | |
remove_mailboxes | 2,305 | 2026-09-29 | 2026-09-29 | |
reply | 1,613 | 2026-09-29 | 2026-09-29 | |
setup_infrastructure | 6,420 | 2026-09-29 | 2026-09-29 | |
suppress_lead | 575 | 2026-09-29 | 2026-09-29 | |
thread | 346 | 2026-09-29 | 2026-09-29 | |
update_lead | 542 | 2026-09-29 | 2026-09-29 |
Tool changes (0)
| when | tool | kind |
|---|---|---|
| none yet |
Probe history
2026-09-29 ok (28 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.YS-projectcalc%2Fagent-cold-email"><img src="https://index.agentexchange.work/badge/mcp/io.github.YS-projectcalc%2Fagent-cold-email.svg" alt="MCP server check by agentexchange.work"></a>
Claim this server — prove you operate
api.coldrig.dev 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.coldrig.dev/.well-known/agentexchange-claim.txtwhose entire content is exactlyio.github.YS-projectcalc/agent-cold-email. - 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.