AI & Machine Learning

aiagentscity.com

Tracks AI agent spending and budgets, manages agent secrets, and reports spend over rolling windows.

x402 supported5 endpoints39 known toolsFirst detected September 14, 2026Last detected September 20, 2026

ENDPOINT 1

https://aiagentscity.com/mcp

No auth detected

MCP server metadata

Name: agent-ledger
Version: 4.0.5

Capabilities

loggingprompts.listChangedresources.listChangedtools.listChanged

Known tools 12

ledger_rotate_secret

Mint a NEW agent_secret for an agent_id your workspace already owns, invalidating the old one.

Inferred read-only

ledger_revoke_secret

Invalidate an agent_id's agent_secret WITHOUT deleting its spend history.

Inferred read-only

ledger_track

Record a spend entry for an AI agent on any payment rail, with optional token counts.

Potential side effects

ledger_set_budget

Set spending caps for an agent.

Inferred read-only

ledger_report

Spend report for an agent over a rolling window.

Inferred read-only

ledger_alerts

Alert history for an agent: budget warnings (80% threshold) and spending spikes.

Inferred read-only

ledger_list_agents

Owner-only: full cross-tenant listing of every agent ever claimed on this instance, with totals.

Inferred read-only

ledger_start

Get a FREE AgentLedger workspace with no credential and no arguments — the MCP equivalent of opening POST /start in a browser.

Potential side effects

ledger_api_docs

Self-serve documentation for AgentLedger — quickstart, MCP tools, REST endpoints, budget caps, error codes, and idempotency usage, as markdown.

Inferred read-only

ledger_examples

Complete, runnable Python recipe for a common AgentLedger integration pattern.

Inferred read-only

skills_list_tool

List this product's skills.

Inferred read-only

read_skill

Read a product skill file by its skill:// URI.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-ledger]
url = "https://aiagentscity.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-ledger": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-ledger
Remote MCP URL: https://aiagentscity.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-ledger": {
      "url": "https://aiagentscity.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-ledger": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-ledger",
  "transport": "streamable-http",
  "url": "https://aiagentscity.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://aiagentscity.com/mcp/agent-watch

No auth detected

MCP server metadata

Name: agent-watch
Version: 1.30.0

Capabilities

experimentalpromptsresourcestools

Known tools 8

aw_health

Liveness check for the Agent Watch API.

Inferred read-only

aw_check_endpoint

Probe an MCP or HTTP-402 endpoint now and get its trust verdict.

Inferred read-only

aw_census

Full-census summary of the official MCP registry: 7,454 endpoints probed with real MCP handshakes.

Inferred read-only

aw_list_monitored

List all endpoints in the Agent Watch census with their registry names.

Inferred read-only

aw_alerts

Show dead endpoints across the monitored registry (alive=false).

Inferred read-only

aw_watch

Add endpoints to your personal watchlist (probed immediately, then every 6h).

Inferred read-only

skills_list_tool

List this product's skills.

Inferred read-only

read_skill

Read a product skill file by its skill:// URI.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-watch]
url = "https://aiagentscity.com/mcp/agent-watch"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-watch": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/agent-watch"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-watch
Remote MCP URL: https://aiagentscity.com/mcp/agent-watch

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-watch": {
      "url": "https://aiagentscity.com/mcp/agent-watch"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-watch": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/agent-watch"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-watch",
  "transport": "streamable-http",
  "url": "https://aiagentscity.com/mcp/agent-watch"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 3

https://aiagentscity.com/mcp/perimeter-watch

No auth detected

MCP server metadata

Name: perimeter-watch
Version: 1.30.0

Capabilities

experimentalpromptsresourcestools

Known tools 6

pw_health

Liveness check for the Perimeter Watch API.

Inferred read-only

pw_snapshot

Run a free one-time external-perimeter scan on a domain you control.

Inferred read-only

pw_watch_status

Check whether a domain is enrolled on a paid weekly monitoring plan.

Inferred read-only

pw_stats

Service funnel counters: page views, snapshots run, paid registrations.

Inferred read-only

skills_list_tool

List this product's skills.

Inferred read-only

read_skill

Read a product skill file by its skill:// URI.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.perimeter-watch]
url = "https://aiagentscity.com/mcp/perimeter-watch"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "perimeter-watch": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/perimeter-watch"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: perimeter-watch
Remote MCP URL: https://aiagentscity.com/mcp/perimeter-watch

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "perimeter-watch": {
      "url": "https://aiagentscity.com/mcp/perimeter-watch"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "perimeter-watch": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/perimeter-watch"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "perimeter-watch",
  "transport": "streamable-http",
  "url": "https://aiagentscity.com/mcp/perimeter-watch"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 4

https://aiagentscity.com/mcp/cited

No auth detected

MCP server metadata

Name: cited
Version: 1.30.0

Capabilities

experimentalpromptsresourcestools

Known tools 9

cited_health

Liveness check for the Cited API.

Inferred read-only

cited_scan

Run a free instant AI-visibility scan for a local business.

Inferred read-only

cited_report

Re-fetch a previous scan result by its shareable scan_id.

Inferred read-only

cited_watch_status

Check whether a business is on the paid weekly monitoring plan.

Inferred read-only

cited_stats

Funnel counters: page views, scans run, paid registrations.

Inferred read-only

cited_api_docs

Self-serve documentation for Cited — quickstart, MCP tools, REST endpoints, error shapes, and agent-operator policies, as markdown.

Inferred read-only

cited_examples

Complete, runnable recipe for a common Cited integration pattern.

Inferred read-only

skills_list_tool

List this product's skills.

Inferred read-only

read_skill

Read a product skill file by its skill:// URI.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.cited]
url = "https://aiagentscity.com/mcp/cited"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "cited": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/cited"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: cited
Remote MCP URL: https://aiagentscity.com/mcp/cited

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "cited": {
      "url": "https://aiagentscity.com/mcp/cited"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "cited": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/cited"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "cited",
  "transport": "streamable-http",
  "url": "https://aiagentscity.com/mcp/cited"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 5

https://aiagentscity.com/mcp/trustscan

No auth detected

MCP server metadata

Name: trust-scan
Version: 4.0.3

Capabilities

loggingprompts.listChangedresources.listChangedtools.listChanged

Known tools 4

trust_scan_server

Security-scan an MCP server or skill package before trusting it.

Inferred read-only

trust_scan_file

Security-scan a single file for invisible Unicode, dangerous patterns, and secrets.

Inferred read-only

skills_list_tool

List this product's skills.

Inferred read-only

read_skill

Read a product skill file by its skill:// URI.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.trust-scan]
url = "https://aiagentscity.com/mcp/trustscan"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "trust-scan": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/trustscan"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: trust-scan
Remote MCP URL: https://aiagentscity.com/mcp/trustscan

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "trust-scan": {
      "url": "https://aiagentscity.com/mcp/trustscan"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "trust-scan": {
      "type": "http",
      "url": "https://aiagentscity.com/mcp/trustscan"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "trust-scan",
  "transport": "streamable-http",
  "url": "https://aiagentscity.com/mcp/trustscan"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.