Agent Economy Index · MCP census · probed 2026-09-29 · JSON
io.github.astafford8488/agentaegis
Verdict: 5 tool description(s) carry model-directed, hidden, secret-material or exfiltration patterns. Endpoint https://agentaegis-mcp-production.up.railway.app/mcp. Latency 13,977 ms.
Tools (28 fingerprinted)
| tool | description length | flags | first seen | last seen |
|---|---|---|---|---|
access_review | 213 | 2026-09-29 | 2026-09-29 | |
account_balance | 168 | secret_material | 2026-09-29 | 2026-09-29 |
agent_history | 167 | 2026-09-29 | 2026-09-29 | |
agent_scan_get | 148 | 2026-09-29 | 2026-09-29 | |
agent_whoami | 170 | secret_material | 2026-09-29 | 2026-09-29 |
audit_report_generate | 282 | 2026-09-29 | 2026-09-29 | |
compliance_framework_check | 268 | 2026-09-29 | 2026-09-29 | |
control_gap_analysis | 182 | 2026-09-29 | 2026-09-29 | |
credential_check | 213 | secret_material | 2026-09-29 | 2026-09-29 |
cve_lookup | 171 | 2026-09-29 | 2026-09-29 | |
dependency_audit | 217 | 2026-09-29 | 2026-09-29 | |
dns_security_check | 210 | 2026-09-29 | 2026-09-29 | |
email_security_audit | 218 | 2026-09-29 | 2026-09-29 | |
evidence_collect | 290 | 2026-09-29 | 2026-09-29 | |
help | 162 | 2026-09-29 | 2026-09-29 | |
incident_triage | 287 | 2026-09-29 | 2026-09-29 | |
mfa_audit | 244 | 2026-09-29 | 2026-09-29 | |
policy_generate | 221 | 2026-09-29 | 2026-09-29 | |
sast_scan | 320 | secret_material | 2026-09-29 | 2026-09-29 |
scan_mcp_plugin | 302 | 2026-09-29 | 2026-09-29 | |
scan_skill | 326 | 2026-09-29 | 2026-09-29 | |
secret_scan | 224 | secret_material | 2026-09-29 | 2026-09-29 |
ssl_tls_audit | 189 | 2026-09-29 | 2026-09-29 | |
threat_intel_lookup | 346 | 2026-09-29 | 2026-09-29 | |
vet_endpoint | 412 | 2026-09-29 | 2026-09-29 | |
vuln_prioritize | 199 | 2026-09-29 | 2026-09-29 | |
vuln_scan_network | 341 | 2026-09-29 | 2026-09-29 | |
vuln_scan_web_app | 235 | 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.astafford8488%2Fagentaegis"><img src="https://index.agentexchange.work/badge/mcp/io.github.astafford8488%2Fagentaegis.svg" alt="MCP server check by agentexchange.work"></a>
Claim this server — prove you operate
agentaegis-mcp-production.up.railway.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.
- Put a text file at
https://agentaegis-mcp-production.up.railway.app/.well-known/agentexchange-claim.txtwhose entire content is exactlyio.github.astafford8488/agentaegis. - 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.