SiteCheck Agent Intel & Dev

Subdomain takeover check: lists up to 10 subdomains seen

agent_intel_subdomain_takeover_monitor

Read-only

Subdomain takeover check: lists up to 10 subdomains seen in certificate transparency logs for a domain (Cert Spotter), fetches each over HTTPS, and flags pages that show a known 'unclaimed service' message (GitHub Pages, S3, Heroku, Fastly). Looks at the page text only, not DNS records, so it can miss dangling records that show no such message. Related tools on this server, for a different need: agent_intel_whale_transaction_monitor when you need large transfers on Ethereum in the latest 1 to 10 blocks. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "<domain>"
    },
    "name": "agent_intel_subdomain_takeover_monitor"
  }
}

Input Schema

Name	Required	Description	Default
`domain`	Yes	Domain such as example.org (a URL is reduced to its host)

Output Schema

Name	Required	Description	Default
`note`	No
`domain`	No
`source`	No
`results`	No
`checkedAt`	No
`checkedSubdomains`	No
`possibleTakeovers`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/openWorld annotations, it discloses the data source (Cert Spotter), the outbound HTTPS fetching behavior, the hard result cap of 10 subdomains, the detection technique and its blind spot, and the exact billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). Those are precisely the operational facts an agent needs for cost and risk reasoning that annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Detection scope, limitation, and pricing are front-loaded in one dense paragraph with little filler, and the cost note at the end is justified. The whale-transaction sibling sentence is the one removable piece — it serves an unrelated need and dilutes the routing signal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only investigation tool with an output schema, the description covers source, method, limits, failure costs and caveats well. It stops short of saying how many of the 10 hosts are actually fetched or how partial failures are reported, which matters for a tool that makes remote requests.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter at 100% schema description coverage, and the schema already explains that a URL is reduced to its host. The prose adds no new meaning about the domain argument (no format, IDN, or subdomain-scope notes), so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource chain: it lists subdomains from certificate transparency logs (Cert Spotter), fetches each over HTTPS, and flags pages matching known 'unclaimed service' signatures for GitHub Pages, S3, Heroku and Fastly. That is far more specific than the title and clearly separates it from siblings like agent_intel_ssl_certificate_transparency or agent_intel_dnssec_trust_chain_validator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear negative qualifier — 'looks at the page text only, not DNS records, so it can miss dangling records' — which tells the agent when results should not be trusted, and the 10-subdomain cap sets expectations. The sibling reference (whale_transaction_monitor) is explicitly labeled 'for a different need', so it does not function as real alternative routing, leaving no true 'use X instead' guidance for the closely related domain-security tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?