Skip to main content
Glama
Sign In

Corrie Site Check

by io.corrie
OverviewDiscussionsAdmin

Check a website's HTTPS and security headers

check_website
Read-onlyIdempotent

Loads the homepage of one public website over HTTPS, the way a visitor's browser would, and reports its HTTPS setup, TLS certificate and security headers (Strict-Transport-Security, Content-Security-Policy, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, cookie flags, mixed content and server banners). Returns a score from 0 to 100, a verdict, the TLS certificate issuer and expiry date, and each finding with a severity (critical, high, medium or low) and a plain-English fix that includes nginx or Cloudflare examples. Use it for questions like 'is example.com secure?', 'what security headers is my site missing?', 'when does this site's certificate expire?' or 'why does Chrome say my site is not secure?'. Input is a bare domain (example.com) or an https:// address. A bare domain checks the homepage; if you include a path, that one page is loaded instead. It does not log in, submit forms, scan ports, crawl other pages or test for vulnerabilities, and nothing is stored. It refuses private, internal and local addresses, plain http://, ports other than 443 and addresses with a user name; those come back as an isError result with a message saying what to change. A check usually takes 1 to 10 seconds. Running it twice on the same site gives the same result unless the site changed. Read corrie://docs/scoring for how the score and verdict work.

Input Schema

NameRequiredDescriptionDefault
urlYesThe public website to check: a bare domain such as example.com, or an https:// address such as https://www.example.com/. If you leave out the scheme, https:// is added. Only port 443 is allowed. Private, internal and local addresses (10.x, 192.168.x, 127.0.0.1, localhost, *.local) are refused.

Output Schema

NameRequiredDescriptionDefault
urlYesThe normalized https:// address that was requested.
scoreYesStarts at 100. Each finding subtracts points: critical 35, high 15, medium 6, low 2. Never below 0.
countsYesNumber of findings at each severity.
verdictYesOne-line summary based on the most severe finding.
findingsYesProblems found, most severe first. Empty when nothing was found.
final_urlYesThe address after following up to 3 redirects.
report_urlYesWhere a person can run the same check in a browser.
certificateYesFacts about the site's TLS certificate. Fields are null when not observed.
http_statusYesHTTP status code of the final response.
limitationsYesWhat this quick check does not cover.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed22 schema fields changed
    • changedInput schema / properties / url / description
      Previous value: -"A public domain or HTTPS address, for example example.com or https://example.com/."New value: +"The public website to check: a bare domain such as example.com, or an https:// address such as https://www.example.com/. If you leave out the scheme, https:// is added. Only port 443 is allowed. Private, internal and local addresses (10.x, 192.168.x, 127.0.0.1, localhost, *.local) are refused."
    • addedInput schema / properties / url / examples
      Added value: +[
+  "example.com",
+  "https://www.example.com/",
+  "shop.example.org"
+]
    • addedInput schema / properties / url / minLength
      Added value: +1
    • addedOutput schema / properties / certificate / description
      Added value: +"Facts about the site's TLS certificate. Fields are null when not observed."
    • addedOutput schema / properties / certificate / properties
      Added value: +{
+  "days_left": {
+    "description": "Whole days until expiry.",
+    "type": [
+      "integer",
+      "null"
+    ]
+  },
+  "expires": {
+    "description": "Expiry date, YYYY-MM-DD (UTC).",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "issuer": {
+    "description": "Issuer common name.",
+    "type": [
+      "string",
+      "null"
+    ]
+  }
+}
    • addedOutput schema / properties / counts / description
      Added value: +"Number of findings at each severity."
    • addedOutput schema / properties / counts / properties
      Added value: +{
+  "critical": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "high": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "low": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "medium": {
+    "minimum": 0,
+    "type": "integer"
+  }
+}
    • addedOutput schema / properties / counts / required
      Added value: +[
+  "critical",
+  "high",
+  "medium",
+  "low"
+]
    • addedOutput schema / properties / final_url / description
      Added value: +"The address after following up to 3 redirects."
    • addedOutput schema / properties / findings / description
      Added value: +"Problems found, most severe first. Empty when nothing was found."
    • addedOutput schema / properties / findings / items / properties
      Added value: +{
+  "category": {
+    "description": "Area of the finding: headers, tls, cookies, mixed_content or reachability.",
+    "type": "string"
+  },
+  "detail": {
+    "description": "What is wrong, in plain English.",
+    "type": "string"
+  },
+  "fix": {
+    "description": "How to fix it, often with an nginx or Cloudflare example.",
+    "type": "string"
+  },
+  "severity": {
+    "description": "How much it matters. See corrie://docs/scoring.",
+    "enum": [
+      "critical",
+      "high",
+      "medium",
+      "low"
+    ],
+    "type": "string"
+  }
+}
    • addedOutput schema / properties / findings / items / required
      Added value: +[
+  "severity",
+  "category",
+  "detail",
+  "fix"
+]
    • addedOutput schema / properties / http_status / description
      Added value: +"HTTP status code of the final response."
    • addedOutput schema / properties / limitations / description
      Added value: +"What this quick check does not cover."
    • addedOutput schema / properties / report_url / description
      Added value: +"Where a person can run the same check in a browser."
    • addedOutput schema / properties / score / description
      Added value: +"Starts at 100. Each finding subtracts points: critical 35, high 15, medium 6, low 2. Never below 0."
    • addedOutput schema / properties / score / maximum
      Added value: +100
    • addedOutput schema / properties / score / minimum
      Added value: +0
    • addedOutput schema / properties / url / description
      Added value: +"The normalized https:// address that was requested."
    • addedOutput schema / properties / verdict / description
      Added value: +"One-line summary based on the most severe finding."
    • addedOutput schema / properties / verdict / enum
      Added value: +[
+  "Needs urgent attention",
+  "A few important fixes",
+  "Looks good, with minor suggestions",
+  "Looks good"
+]
    • changedOutput schema / required
      Previous value: -[
-  "url",
-  "score",
-  "verdict",
-  "findings"
-]New value: +[
+  "url",
+  "final_url",
+  "http_status",
+  "score",
+  "verdict",
+  "counts",
+  "findings",
+  "certificate",
+  "limitations",
+  "report_url"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses refusal cases (private/internal/local, plain http, non-443 ports, user names) and the isError outcome, latency (1-10s), idempotency caveat ('same result unless the site changed'), statelessness ('nothing is stored'), and a pointer to corrie://docs/scoring for the scoring model. Annotations only cover safety hints, and the description adds substantive operational context on top.

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?

It is a long description, but it is front-loaded (what it loads, what it returns) before examples, exclusions and limits. Nearly every sentence carries distinct, decision-relevant information, though the enumeration of headers and the examples section could be trimmed slightly.

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?

Output schema exists, so return-value explanation was not required, yet the description still maps the result shape (score, verdict, certificate issuer/expiry, findings with severity and fixes). Combined with the refusal behavior and timing, an agent has everything needed to call this correctly and interpret failures.

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 baseline is 3, but the description adds meaning the schema does not: bare domain checks the homepage while including a path loads only that page instead. That is a genuine semantic addition beyond the documented parameter.

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 — loads a public website's homepage over HTTPS and reports its HTTPS/TLS/header posture. The scope is exact enough that an agent knows precisely what is and is not covered; no sibling tools exist to disambiguate from.

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 concrete trigger questions ('is example.com secure?', 'what headers is my site missing?', 'why does Chrome say my site is not secure?') and explicit exclusions (no logins, forms, port scans, crawling or vulnerability testing). It also spells out the refused input classes and that they surface as isError with a corrective message, so routing is unambiguous.

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

All Corrie Site Check toolsInspect
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