SiteCheck Web Intel

Checks the live HTTP response headers of a site's home page

security_security_headers

Read-only

Checks the live HTTP response headers of a site's home page (one GET, https) for Content-Security-Policy, Strict-Transport-Security, X-Content-Type-Options, X-Frame-Options, Referrer-Policy, Permissions-Policy and Cross-Origin-Opener-Policy. Returns present/missing headers with their values and a score out of 7. It does not judge the quality of the values. Related tools on this server, for a different need: security_spameatingmonkey when you need to check an IPv4 mail-sending address against; security_cookie_security when you need to list the cookies a site sets on its public home page. 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": "security_security_headers"
  }
}

Input Schema

Name	Required	Description	Default
`domain`	Yes	Domain name such as wikipedia.org (required)

Output Schema

Name	Required	Description	Default
`score`	No
`domain`	No
`source`	No
`missing`	No
`present`	No
`finalUrl`	No
`maxScore`	No
`checkedAt`	No
`httpStatus`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses scope limits (single request, HTTPS, home page only), an epistemic caveat ('does not judge the quality of the values'), and concrete cost mechanics ($0.002 per successful call via x402 with no charge on failure). That pricing and non-judgment note are exactly the traits an agent cannot get from structured fields.

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?

Front-loads the action and header list, then tacks on return shape, exclusions, alternatives, and pricing; every clause carries information. The single dense paragraph is a bit of a run-on and the sibling/pricing tail could be separated for faster scanning.

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

Completeness5/5

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

An output schema exists, and the description still summarizes the return conceptually (present/missing headers with values plus a 0-7 score), so the agent knows what to expect without reading it. For a single-parameter read-only probe, nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

With one parameter at 100% schema coverage the baseline is already high, and the description still adds meaning by pinning the target to a bare domain home page over HTTPS rather than an arbitrary URL. It adds scoping value without introducing ambiguity.

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?

States a specific verb and resource (checks live HTTP response headers of a site's home page), enumerates the seven headers examined, and describes the result shape (present/missing plus score out of 7). It also explicitly separates itself from two named siblings, so an agent can route without opening any schema.

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?

Gives clear context ('one GET, https', home page only) and names two alternative tools with the condition that selects each (spameatingmonkey for IPv4 mail-sending reputation, cookie_security for listing cookies). It stops short of addressing the closest overlaps on this server, such as csp_evaluator_audit or referrer_policy_audit, so the agent must still infer those boundaries.

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

All SiteCheck Web Intel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?