Skip to main content
Glama
Website Security Audit MCP Server

Website Security Audit MCP Server

by eazetech-co

Check security headers

check_security_headers
Read-only

Fetches a public web page and reports its HTTPS redirect chain, security response headers, and cookie flags with a fix for each problem, without checking TLS or page content.

Instructions

Fetches a public web page, following up to 5 redirects, and reports its HTTPS redirect chain, security response headers and cookie flags, with a fix for each problem. Faster than audit_website_security and gives no grade: it does not check TLS, the certificate, DNS, email records or page content. Refuses IP addresses, ports other than 80 and 443, and any host that resolves to a private, loopback, link-local, carrier-grade NAT or cloud metadata address.

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": {
      "url": "<url>"
    },
    "name": "check_security_headers"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesWebsite address to check, such as example.com or https://example.com/. Only http and https on ports 80 and 443. Any query string is removed before the request.

Output Schema

NameRequiredDescriptionDefault
notesYesChecks that did not finish, were skipped or saw partial data
countsYes
domainYes
targetYesFinal address after redirects, without query string
headersYesValues from the final response, cleaned and shortened. A header that is not set is left out.
findingsYes
redirectsYes
scannedAtYes
durationMsYes
cookieCountYesNumber of Set-Cookie headers on the final response

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavior beyond them: a redirect-following cap of 5, the refusal policy for hosts and ports, and the removal of query strings before the request. These are the failure modes an agent would otherwise discover only by erroring out.

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

Conciseness5/5

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

Three sentences, each load-bearing: capability and output first, sibling differentiation second, refusal rules last. No filler or restatement of the title, and the most decision-relevant facts are front-loaded.

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, so return values need not be explained, and the description still covers redirect behavior, scope limits, and input rejection rules. For a single-parameter read-only fetch tool this leaves no meaningful gap for correct invocation.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents the url format, port restrictions, and query-string stripping. The description adds no additional syntax or format meaning beyond the schema, 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?

States a concrete verb and resource (fetches a public web page and reports HTTPS redirect chain, security headers, cookie flags, plus a fix per problem). It also names the sibling audit_website_security and draws an explicit boundary (faster, no grade), so an agent can pick between the two without opening either schema.

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

Usage Guidelines5/5

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

Gives explicit when-not guidance: it does not check TLS, the certificate, DNS, email records, or page content, which routes those needs to audit_website_security. It also states hard input constraints (no IP addresses, only ports 80/443, no hosts resolving to private/loopback/link-local/CGNAT/metadata addresses), which is exactly the pre-call check an agent needs.

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