AgentLedger
Per-agent spend management for AI agents: budget caps enforced before the provider is charged, spend tracking across x402/MPP/API-key rails, anomaly alerts, and audit trails.
Hosted MCP Server
npx add-mcp 'https://aiagentscity.com/mcp/'Installs into Claude Code, Codex, Cursor and more
Documentation
The operations layer agents run on.
Budgets, monitoring, security, trust, discovery — five products, one MCP catalog, zero human required. Read the contract, connect, transact.
agent sessionlive
discoverGET /.well-known/x402.json 200 · mainnet eip155:8453 · accepts USDC
connectmcp add agent-ledger https://aiagentscity.com/mcp/ 14 tools · ledger_track · ledger_set_budget …
transactPOST /v1/billing/x402 · X-PAYMENT: <signed> 200 · 24h Pro · $0.01 USDC settled
enforceledger_set_budget {agent:"researcher", monthly:$50}cap armed · over-budget calls → 402 pre-provider
the agent-native surface, playing next to the contract — the whole site works like this
agent-ledger14 toolsclaude mcp add --transport http agent-ledger https://aiagentscity.com/mcp/
agent-watch8 toolsclaude mcp add --transport http agent-watch https://aiagentscity.com/mcp/agent-watch/
perimeter-watch6 toolsclaude mcp add --transport http perimeter-watch https://aiagentscity.com/mcp/perimeter-watch/
trustscan4 toolsclaude mcp add --transport http trustscan https://aiagentscity.com/mcp/trustscan/
cited9 toolsclaude mcp add --transport http cited https://aiagentscity.com/mcp/cited/
x402 · Base mainnet
$0.01 · zero clicks.
POST /v1/billing/x402 + X-PAYMENT header → 24h AgentLedger Pro on the workspace your wallet resolves to. No signup flow, no card form, no human.
Five products, one contract.
Every product is MCP-native. Tool counts are the live tools/list output, not marketing.
01 · Control spend · Flagship 14 tools
AgentLedger — spending limits for AI agents
Per-agent spend caps with 402 enforcement before the provider is ever called. The call that would break the budget never reaches the provider.
02 · Monitor 8 tools
Agent Watch
Monitoring for the agent economy. Know the moment a new agent touches your API.
03 · Secure 6 tools
Perimeter Watch
Dangling DNS, expiring certs, lookalike domains — caught before they're incidents.
04 · Trust 4 tools
TrustScan
Scan before you trust. Know who you're dealing with before your agent does.
05 · Be found 9 tools
Cited
Does AI recommend your practice? Instant scan, verbatim evidence.
machine entry points
/.well-known/x402.json · /skill.md · /openapi.json · /server.json · /.well-known/mcp.json · /status · /llms.txt
Agents are economic actors now.
They spend money. They call your APIs. They represent businesses. AI Agent City is the operations layer they run on — budgets, monitoring, security, trust, and discovery. Live software, not slides.
MCP · tool protocol x402 · payment protocol Base · eip155:8453 USDC · settlement llms.txt · discovery
01
Agents hold wallets
Machine-to-machine payments settle on-chain for fractions of a cent. The moment agents spend, someone has to set the budget.
02
Agents call your APIs
Non-human traffic already hits production endpoints, and most teams can't see it. You can't secure or bill what you can't attribute.
03
AI answers are the new search
Customers ask ChatGPT and Claude instead of Googling. If the models don't recommend you — with receipts — you're invisible.
"Every economic actor needs five things: a budget, a monitor, a perimeter, a reputation, and a way to be found. We're building all five — for agents."
One stack. Five products.
Each solves one operational problem end to end. Each is live and independently usable.
01 · Control spend · Flagship 14 tools
AgentLedger — spending limits for AI agents
Per-agent spend caps with 402 enforcement before the provider is ever called. The call that would break the budget never reaches the provider.
02 · Monitor 8 tools
Agent Watch
Monitoring for the agent economy. Know the moment a new agent touches your API.
03 · Secure 6 tools
Perimeter Watch
Dangling DNS, expiring certs, lookalike domains — caught before they're incidents.
04 · Trust 4 tools
TrustScan
Scan before you trust. Know who you're dealing with before your agent does.
05 · Be found 9 tools
Cited
Does AI recommend your practice? Instant scan, verbatim evidence.
Live, not slides.
$0.01, zero clicks
An agent bought 24h of AgentLedger Pro over x402 on Base mainnet — real USDC, no human in the loop.
402, not a dashboard
Trace viewers report after you've paid. AgentLedger refuses the over-budget call before the provider sees it.
Priced honestly
Flat-rate token pricing was 7.4× wrong on a real session. AgentLedger prices cache-aware.
Recent ships, dated.
The changelog is the proof the stack is alive — every entry is a shipped outcome, not a progress update.
2026-09-21
Access vs spend. A positioning page: /manifesto — Kiteworks governs what agents can touch, AgentLedger governs what agents can spend. Complementary halves, and only one of them has an owner yet. platform
2026-09-20
MCP verified end-to-end. Handshake and tools/list confirmed for all five products — 12, 8, 6, 4 and 9 tools. The stale "dispatch needs repair" warnings were retired from every product page. platform
2026-09-19
Satellite MCP endpoints mounted. /mcp/agent-watch, /mcp/perimeter-watch, /mcp/cited and /mcp/trustscan resolve instead of 404ing. platform
2026-09-16
x402 live on Base mainnet. $0.01 USDC → 24h of AgentLedger Pro. Agents buy with zero human clicks. agent-ledger