AgentLedger is a remote MCP server that gives an AI agent 9 tools, among them ledger_alerts, ledger_api_docs, ledger_examples. It answers at https://aiagentscity.com/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Per-agent spend management: x402/MPP/API-key rails, budget caps, anomaly alerts, audit trails.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ledger_alerts | Alert 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). Inputs: agent_id, agent_secret, workspace_key |
ledger_api_docs | Self-serve documentation for AgentLedger — quickstart, MCP tools, REST endpoints, budget caps, error codes, and idempotency usage, as markdown. Inputs: topic |
ledger_examples | Complete, runnable Python recipe for a common AgentLedger integration pattern. Inputs: pattern |
ledger_list_agents | Owner-only: full cross-tenant listing of every agent ever claimed on this instance, with totals. Requires the operator's admin_secret — this is a portfolio-wide view, not a per-agent report (use ledger_report for that — it requires that age Inputs: admin_secret |
ledger_report | Spend 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's own agent_secret or Inputs: agent_id, days, agent_secret, workspace_key |
ledger_revoke_secret | Invalidate 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 rotate a new secret in. Inputs: agent_id, workspace_key |
ledger_rotate_secret | Mint 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 workspace_key that owns agent Inputs: agent_id, workspace_key |
ledger_set_budget | Set 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/ daily_tokens) are indepen Inputs: agent_id, monthly_cents, daily_cents, monthly_tokens, daily_tokens, agent_secret |
ledger_track | Record 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 /start). That first call Inputs: agent_id, rail, amount_cents, service, tokens_in, tokens_out |
Every block below points at https://aiagentscity.com/mcp/. Pick your client and copy.
claude mcp add --transport http agentledger https://aiagentscity.com/mcp/
{
"mcpServers": {
"agentledger": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://aiagentscity.com/mcp/"]
}
}
}{
"mcpServers": {
"agentledger": {
"url": "https://aiagentscity.com/mcp/"
}
}
}{
"servers": {
"agentledger": {
"type": "http",
"url": "https://aiagentscity.com/mcp/"
}
}
}{
"context_servers": {
"agentledger": {
"url": "https://aiagentscity.com/mcp/"
}
}
}{
"mcpServers": {
"agentledger": {
"serverUrl": "https://aiagentscity.com/mcp/"
}
}
}{
"mcpServers": {
"agentledger": {
"url": "https://aiagentscity.com/mcp/"
}
}
}name: AgentLedger
version: 0.0.1
schema: v1
mcpServers:
- name: AgentLedger
type: streamable-http
url: https://aiagentscity.com/mcp/{
"mcpServers": {
"agentledger": {
"httpUrl": "https://aiagentscity.com/mcp/"
}
}
}{
"mcpServers": {
"agentledger": {
"type": "http",
"url": "https://aiagentscity.com/mcp/"
}
}
}{
"mcpServers": {
"agentledger": {
"url": "https://aiagentscity.com/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Faiagentscity.com%2Fmcp%2F&type=streamable_http&id=agentledger&name=AgentLedger
It answered our last check on 22 October 2026 in 276 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 14 September 2026: ledger_alerts, ledger_api_docs, ledger_examples, ledger_list_agents, ledger_report, ledger_revoke_secret, ledger_rotate_secret, ledger_set_budget, and 1 more.
It answered our last check on 22 October 2026 in 276 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://aiagentscity.com/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.entradox. Endpoint host: aiagentscity.com. ARD identifier: urn:air:io.github.entradox:mcp:agent-ledger.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.