Observed arrival · 2026-11-10
SpotAgentIQ puts a human checkpoint between AI agents and risky tool calls
An open-source MCP proxy lets AI agent tool calls pass, get blocked, or wait for human approval under configurable rules.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Teams running MCP-connected AI agents
- Worth noticing
- Policies combine first-match rules, tool-name globs, argument checks, and configurable redaction keys.
Field notes
The policy example starts with a default allow action, then applies ordered rules for card-like arguments, outbound email, deletion, and Stripe calls. The page says the proxy can redact named keys at any depth and describes approval through an inbox, with Slack available if configured. Installation is presented as one Go binary; the cloud offering is still described as coming.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue