Skip to main content
Glama
Website Security Audit MCP Server

Website Security Audit MCP Server

by eazetech-co

Audit website security

audit_website_security
Read-only

Runs a passive security audit of a public website, returning a score, grade, and findings with fixes. Checks HTTPS, headers, cookies, TLS, email records, and vulnerable scripts without intrusive requests.

Instructions

Runs a passive security audit of a public website and returns a score out of 100, a grade from A+ to F, and findings with a fix for each. Checks HTTPS and redirects, security headers, cookie flags, TLS versions and the certificate, SPF, DMARC, MTA-STS, CAA and name servers, dangling CNAME records, third-party scripts, known-vulnerable JavaScript libraries, mixed content, forms, version disclosure and security.txt. Requests only what the site serves to any visitor. Takes 5 to 40 seconds. 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": "audit_website_security"
  }
}

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
gradeYes
notesYesChecks that did not finish, were skipped or saw partial data
scoreYes
cachedYesTrue when this result was reused from a scan of the same address in the last minute
countsYes
domainYes
targetYesFinal address after redirects, without query string
findingsYesSorted from critical to pass
redirectsYes
scannedAtYesISO 8601 time of the scan
durationMsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that the audit is passive and only requests what any visitor would receive, quantifies latency at 5 to 40 seconds, and spells out the SSRF-style target restrictions. That is exactly the operational context an agent needs before invoking an open-world network tool.

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-loaded with purpose and outputs, then constraints and timing. The long enumeration of individual checks is the only soft spot — it is dense but does real work by defining audit scope and implicitly differentiating from narrower sibling tools.

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, yet the description still summarizes the return shape (score, grade, findings with fixes), and it covers timing, safety posture and input rejection rules. For a one-parameter, read-only audit tool, nothing an agent needs in order 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?

Schema coverage is 100%, so the single url parameter is already documented including scheme and port limits and query-string stripping. The description adds meaning the schema does not: IP addresses and private/reserved resolutions are rejected, which tells the agent what inputs will fail before it calls.

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 ('Runs a passive security audit of a public website') and immediately names the outputs (score out of 100, grade A+ to F, findings with fixes). The enumerated check list makes the scope concrete and clearly broader than the sibling header/security.txt checkers, so an agent can distinguish them without opening a 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 negative conditions: it refuses IP addresses, ports other than 80/443, and hosts resolving to private, loopback, link-local, CGNAT or metadata addresses. It also sets an expectation of 5 to 40 seconds. What it lacks is an explicit routing statement pointing to check_security_headers or check_security_txt for narrower checks.

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