// SCAN REPORT

Agent Toolbox

13 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

1 can modify or destroy data

12 read-only

13 tools total

Community server · catalogue entry verified 29/06/2026

How to control Agent Toolbox ↓

TOOL MAP

What Agent Toolbox exposes to your agents

Read (12) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Agent Toolbox tools

Write · Medium qr_generate Generate a QR code (PNG base64 or SVG)

1 of Agent Toolbox's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Agent Toolbox

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Toolbox, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "qr_generate": {
    "limits": [
      {
        "counter": "qr_generate_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "dns": {
    "limits": [
      {
        "counter": "dns_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Agent Toolbox — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AGENT TOOLBOX →

Instant setup, no code required.

FULL CATALOGUE

All 13 Agent Toolbox tools

WRITE 1 tools

Write qr_generate Generate a QR code (PNG base64 or SVG)

READ 12 tools

Read dns DNS record lookup — A, AAAA, CNAME, MX, NS, TXT, SOA, SRV, CAA Read extract Extract content from a web page using Readability Read finance Get stock quotes, history, or exchange rates Read geoip IP geolocation lookup — country, city, coordinates, timezone, ISP Read news Search news articles from Google News Read pdf_extract Extract text from a PDF URL Read screenshot Take a screenshot of a web page Read search Search the web using DuckDuckGo Read translate Translate text between 100+ languages Read validate_email Validate an email address (syntax, MX, SMTP, disposable detection) Read weather Get weather forecast for a location Read whois WHOIS domain lookup — registrar, dates, nameservers, registrant

FAQ

Questions about Agent Toolbox

How do I prevent bulk modifications through Agent Toolbox? +

The Agent Toolbox server has 1 write tools including qr_generate. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Agent Toolbox.

How many tools does the Agent Toolbox MCP server expose? +

13 tools across 2 categories: Read, Write. 12 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Agent Toolbox? +

Register the Agent Toolbox MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Agent Toolbox tool call.

Deterministic rules across all 13 Agent Toolbox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT TOOLBOX →

Instant setup, no code required.

13 Agent Toolbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.