Skip to main content
Glama

cors_checker

Read-only

Would a browser on this origin be allowed to read this URL? Verdict allowed | blocked | unknown, the reason, and the header to add. Only GET and HEAD are really sent: other methods measure the preflight alone. Many origins at once: cors_test.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://www.ia-qa.com/mcp"
    },
    "name": "cors_checker"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesFull URL to test, e.g. https://api.example.com/resource
methodNoMethod the page uses (default: GET)
originNoOrigin of the calling page (default: https://yourdomain.com)
credentialsNoTrue for fetch with credentials: "include"
request_headersNoHeaders the page sets, e.g. ["Authorization", "Content-Type: application/json"]. Names only are sent.

Output Schema

NameRequiredDescriptionDefault
fixNo
checksNo
reasonNo
statusNo
verdictNo
preflightNo
corsHeadersNo
request_sentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • addedInput schema / properties / credentials
      Added value: +{
      +  "description": "True for fetch with credentials: \"include\"",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / method / description
      Previous value: -"HTTP method to simulate (default: GET)"New value: +"Method the page uses (default: GET)"
    • changedInput schema / properties / origin / description
      Previous value: -"Origin header to simulate (default: https://yourdomain.com)"New value: +"Origin of the calling page (default: https://yourdomain.com)"
    • addedInput schema / properties / request_headers
      Added value: +{
      +  "description": "Headers the page sets, e.g. [\"Authorization\", \"Content-Type: application/json\"]. Names only are sent.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedOutput schema / properties / allHeaders
      Removed value: -{}
    • addedOutput schema / properties / checks
      Added value: +{}
    • addedOutput schema / properties / fix
      Added value: +{}
    • removedOutput schema / properties / method
      Removed value: -{}
    • addedOutput schema / properties / reason
      Added value: +{}
    • addedOutput schema / properties / request_sent
      Added value: +{}
    • removedOutput schema / properties / testedOrigin
      Removed value: -{}
    • removedOutput schema / properties / url
      Removed value: -{}
    • addedOutput schema / properties / verdict
      Added value: +{
      +  "enum": [
      +    "allowed",
      +    "blocked",
      +    "unknown"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "url": "https://www.ia-qa.com/mcp"
      +  }
      +]
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond them: only GET and HEAD actually send a request, while other methods measure the preflight alone, and it previews the verdict vocabulary. It does not mention rate limits, timeouts, or whether failures surface as 'unknown' versus an error.

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?

Three short sentences, front-loaded with the core question, then the return shape, then the operational caveats and the sibling pointer. The middle sentence is a fragment ("Verdict allowed | blocked | unknown, the reason, and the header to add") that reads slightly clipped, but no sentence is wasted.

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?

With an output schema present, the description need not explain return values in detail, yet it still names the verdict set and the remediation header. Annotations carry the read-only/open-world profile, the schema documents all five parameters, and the description supplies the one non-obvious behavior (preflight-only for non-GET/HEAD) plus the multi-origin routing. Nothing essential to calling 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 baseline would be 3, but the description adds meaning the schema does not: it clarifies that the method parameter changes what is actually exercised on the wire (real request for GET/HEAD, preflight-only otherwise). The origin parameter is framed by the opening question, giving it context beyond "origin of the calling page".

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 opening question states a specific, unambiguous purpose: determining whether a browser on a given origin may read a given URL, i.e. a CORS check. It also states what the tool returns (verdict allowed | blocked | unknown, reason, header to add) and names the sibling cors_test for the multi-origin case, so an agent can separate it from cors_test and web_security_audit 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 Guidelines4/5

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

"Many origins at once: cors_test" gives an explicit routing rule to the alternative tool, and the GET/HEAD caveat tells the caller which method values produce a real request versus a preflight-only measurement. What is missing is a positive statement of when this tool is the right choice (e.g. single-origin verification of a page you are debugging) and any note about live network reachability requirements.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.