// human-readable · aiagentscity.com/products

One stack.
Five products.

Each solves one operational problem end to end. Each is live, independently usable, and agent-callable — MCP everywhere; REST + CLI on AgentLedger.

01 — CONTROL SPEND · FLAGSHIP v0.4.1 · 12 tools

AgentLedger — spending limits for AI agents

Your agents spend money. Give each one a spending limit. Meters every call, shows a live P&L per agent, and refuses the call that would cross the budget — before the provider is contacted.

  • Pre-provider enforcement — the proxy estimates max cost and returns 402. The provider never sees the request; the money is never spent.
  • Cache-aware pricing — real tokens × real model rates. Flat-rate was 7.4× wrong on a real session.
  • Agents buy their own Pro — $0.01 x402 on Base mainnet, 24h, zero human clicks.
  • Push alerts + shareable reports — webhooks with retries; signed, expiring report links.
HTTP/1.1 402 Payment Required
{"error":{"type":"budget_exceeded", "message":"blocked before the provider"}}

Free: 3 agents, every rail, enforced caps. Pro: $19/mo flat — unlimited agents, never per seat.

02 — MONITOR v1.30.0 · 8 MCP tools

Agent Watch — monitoring for the agent economy

Non-human traffic is hitting your APIs and you can't see it. What changed this week, alerts the moment a new agent calls your endpoints, anomaly summaries — before they become incidents or invoices.

"Alert me when a new agent calls our API, with a weekly activity summary."

Status: the MCP endpoint is up and lists tools; tool execution on the satellite backend is being repaired (Sept 2026).

03 — SECURE v1.30.0 · 6 MCP tools

Perimeter Watch — passive external-perimeter monitoring for web agencies

Attackers view your clients' domains from the outside. So do we. Dangling DNS, expiring certs, lookalike domains — scanned passively, briefed weekly.

"Scan example.com for dangling DNS and cert expiry, then check lookalikes."

Status: the MCP endpoint is up and lists tools; tool execution on the satellite backend is being repaired (Sept 2026). The free browser snapshot works today.

04 — TRUST v4.0.3 · 4 MCP tools · live

TrustScan — scan before you trust

Your agent is about to install a stranger's MCP server. TrustScan answers the question every agent should ask first: is this safe to wire in? Invisible-Unicode prompt-injection, dangerous code patterns (MCP001–MCP006), hardcoded secrets, typosquat names — a 0–100 score, a letter grade, and evidence. Live over MCP today, read-only, no signup.

05 — BE FOUND v1.30.0 · 9 MCP tools

Cited — does AI recommend your practice?

Your customers stopped Googling. They ask AI. Instant scan of what the AI engines say about your business — with verbatim evidence. Free.

"Scan Gentry Dentistry of Suwanee for AI visibility — verbatim quotes."

Status: the MCP endpoint is up and lists tools; tool execution on the satellite backend is being repaired (Sept 2026). The free browser scan works today.

Five products, one thesis: the agent economy needs operations. We're building the boring infrastructure that makes the exciting future possible.
// machine-readable · what an agent sees on /products
$ agent-view /products
products:
  - id: agent-ledger · mcp: /mcp/ (12 tools) · rest: /v1/*
    pricing: {free: "≤3 agents", pro: "$19/mo flat"} · x402: "$0.01 = 24h Pro"
  - id: agent-watch · mcp: /mcp/agent-watch (8 tools) · status: degraded (tool execution being repaired)
  - id: perimeter-watch · mcp: /mcp/perimeter-watch (6 tools) · status: degraded (tool execution being repaired) · free_snapshot: https://entradox.github.io/perimeter-watch-site/
  - id: trustscan · mcp: /mcp/trustscan (4 tools · v4.0.3) · live
  - id: cited · mcp: /mcp/cited (9 tools) · status: degraded (tool execution being repaired) · free_scan: https://entradox.github.io/cited-site/
capabilities: [spend-caps, monitoring, perimeter-scan, trust-scan, ai-visibility]
auth: workspace_key (human) | X-PAYMENT x402 (agent, no human)