AgentLedger
OnlineMeter, cap, and block AI agent spend before the provider is charged.
What it can do: 18 tools
ledger_rotate_secretMint a NEW agent_secret for an agent_id your workspace already owns, invalidating the old one. Use this to RECOVER an agent whose secret was lost: the previous credential stops working immediately. Requires the workspacledger_revoke_secretInvalidate an agent_id's agent_secret WITHOUT deleting its spend history. Use when a credential may have leaked, or to stop an agent writing. Subsequent writes to that agent fail with agent_secret_mismatch until you rotledger_trackRecord a spend entry for an AI agent on any payment rail, with optional token counts. Claiming a brand-new agent_id requires your workspace_key (get one via x402 at POST /v1/billing/x402 — no human, no login — or at /stledger_set_budgetSet spending caps for an agent. Warns at 80%, blocks spend when exceeded — enforced: a ledger_track call that would cross the cap is rejected. Dollar caps (monthly_cents/daily_cents) and token caps (monthly_tokens/ dailledger_reportread-onlySpend report for an agent over a rolling window. Returns total spend, breakdown by rail and by service, budget status (ok/warning/exceeded), detected anomalies, and entry count. Requires a credential: either the agent'ledger_proxy_attachread-onlyPoint your provider traffic at the proxy so budget caps are enforced BEFORE the provider is contacted, instead of being reported afterwards. This closes the gap where the brake was unreachable from MCP: an agent connectledger_alertsread-onlyAlert history for an agent: budget warnings (80% threshold) and spending spikes. Requires a credential: either the agent's own agent_secret or its workspace's workspace_key (same rule as GET /v1/alerts).ledger_wait_eventsread-onlyLong-poll an agent's event feed — how an agent with no public URL receives alerts. Webhooks (POST /v1/webhooks) push events to a URL you own; an agent on stdio MCP cannot host one, so it waits here instead. Call this inledger_check_spendread-onlyAsk BEFORE you spend: may this agent spend this much right now? Returns allowed (true/false), a stable reason code (within_budget, over_monthly_cap, over_daily_cap, over_monthly_token_cap, over_daily_token_cap, no_budgeledger_request_approvalAsk your workspace owner for a one-shot spend exception before a ledger_track that the cap would refuse. Creates a pending permit for exactly amount_cents on the given service. The owner (a human, or a supervisor agentledger_approvalsread-onlyList spend-approval permits — yours, or your whole workspace's.ledger_approval_decideApprove or deny a pending spend permit — workspace owner only. The agent's own agent_secret can REQUEST an approval but can never decide one: a credential that can approve its own requests is not a control. decision musledger_priceread-onlyWhat will this call cost? Priced from the same table the caps use. Exists because ledger_track requires the CALLER to supply amount_cents, so an agent whose spend is capped could under-report its own cost and stay underledger_startGet a FREE AgentLedger workspace with no credential and no arguments — the MCP equivalent of opening POST /start in a browser. Call this FIRST if you have no credentials yet. Every other tool here (ledger_track, ledger_ledger_api_docsread-onlySelf-serve documentation for AgentLedger — quickstart, MCP tools, REST endpoints, budget caps, error codes, and idempotency usage, as markdown.ledger_examplesread-onlyComplete, runnable Python recipe for a common AgentLedger integration pattern.skills_list_toolList this product's skills. Each entry carries the SKILL.md URI, its name and description, verbatim frontmatter, and a per-file sha256 manifest. Read a body with `read_skill`.read_skillRead a product skill file by its skill:// URI.
Connect it
claude mcp add --transport http agentledger https://aiagentscity.com/mcp/Settings → Connectors → Add custom connector
URL: https://aiagentscity.com/mcp/{
"mcpServers": {
"agentledger": {
"url": "https://aiagentscity.com/mcp/"
}
}
}{
"servers": {
"agentledger": {
"type": "http",
"url": "https://aiagentscity.com/mcp/"
}
}
}Questions
What does AgentLedger do?
Meter, cap, and block AI agent spend before the provider is charged. It exposes 18 tools to AI assistants.
What tools does AgentLedger provide?
18 tools, including ledger_rotate_secret, ledger_revoke_secret, ledger_track, ledger_set_budget, ledger_report, ledger_proxy_attach, ledger_alerts, ledger_wait_events, ledger_check_spend, ledger_request_approval, ledger_approvals, ledger_approval_decide….
How do I connect AgentLedger to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://aiagentscity.com/mcp/ as a custom connector or MCP server. Copy-paste setup is on this page.
Does AgentLedger require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is AgentLedger online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes AgentLedger?
@entradox on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.
Similar in Finance & Payments
-
TipRanksOnlineOfficial
Live TipRanks market data: analyst ratings, Smart Score, technicals, options, portfolios.
-
GoCardless MCP ServerOnline · sign-in requiredOfficial
Manage GoCardless payments, mandates, subscriptions, refunds and payouts via AI assistants.
-
Avalara AvaTaxOnline · sign-in requiredOfficial
Access Avalara AvaTax API for tax calculation, transactions, nexus management, and compliance
-
Avalara ReturnsOnline · sign-in requiredOfficial
Provides access to Avalara Global Returns API for tax returns, filing calendars, and compliance data
-
Avalara Tax ContentOnline · sign-in requiredOfficial
Provides access to Avalara Tax Content: TTE configs, jobs, communications, lodging, autorental
-
Avalara Tax Registrations and Business LicensesOnline · sign-in requiredOfficial
Provides access to Avalara Tax Registration and Business Licenses APIs for filings and registrations