Agents Index

AgentLedger

Online

Meter, cap, and block AI agent spend before the provider is charged.

Visit publisherConnectJSON

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 workspac
  • ledger_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 rot
  • ledger_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 /st
  • ledger_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/ dail
  • ledger_report read-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_attach read-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 connect
  • ledger_alerts read-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_events read-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 in
  • ledger_check_spend read-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_budge
  • ledger_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 agent
  • ledger_approvals read-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 mus
  • ledger_price read-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 under
  • ledger_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_docs read-onlySelf-serve documentation for AgentLedger — quickstart, MCP tools, REST endpoints, budget caps, error codes, and idempotency usage, as markdown.
  • ledger_examples read-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 Code
claude mcp add --transport http agentledger https://aiagentscity.com/mcp/
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://aiagentscity.com/mcp/
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "agentledger": {
      "url": "https://aiagentscity.com/mcp/"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "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