Skip to main content
Glama

mcp-server

by com.httpstatus
OverviewDiscussionsAdmin

Check CORS

check_cors
Read-onlyIdempotent

Read-only CORS diagnostic. Sends an OPTIONS preflight (Origin plus Access-Control-Request-Method set to method) and one GET/HEAD request with an Origin header, then returns the Access-Control-Allow-* headers and an allowed/blocked verdict with reasons. The target is only ever sent OPTIONS, GET or HEAD; method is just the method being evaluated. Follows the Fetch standard CORS protocol (https://fetch.spec.whatwg.org/#http-cors-protocol).

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute http(s) URL. Private, loopback and cloud-metadata addresses are rejected.
methodNoHTTP method the browser would use (default GET). It is only evaluated against the preflight response and is never sent to the target.GET
originYesBrowser origin making the request, e.g. https://app.example.com
requestHeadersNoComma-separated custom request headers, e.g. "authorization, content-type"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / method / description
      Added value: +"HTTP method the browser would use (default GET). It is only evaluated against the preflight response and is never sent to the target."
    • removedInput schema / properties / method / enum
      Removed value: -[
-  "GET",
-  "HEAD",
-  "POST",
-  "PUT",
-  "PATCH",
-  "DELETE",
-  "OPTIONS"
-]
    • addedInput schema / properties / method / pattern
      Added value: +"^[A-Za-z]{3,10}$"
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description goes well beyond them by disclosing the precise network traffic sent, that the target only ever receives OPTIONS/GET/HEAD, and that `method` is evaluated but never transmitted. That is exactly the behavioral context an agent needs for an outbound probe.

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, front-loaded with the read-only diagnostic framing and what is sent, then the safety guarantee, then the protocol reference. Every sentence carries information; nothing is padding.

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

Completeness4/5

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

With no output schema, the description usefully names the return payload (Access-Control-Allow-* headers plus an allowed/blocked verdict with reasons), which compensates well. Minor omissions remain, such as redirect or timeout behavior, so it is complete enough but not exhaustive.

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?

Schema description coverage is 100%, so all four parameters are already documented in the schema, including the note that `method` is only evaluated. The description restates the `method` semantics and the Origin/ACRM header composition but adds no new syntax or format detail, so the baseline 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 specific verb and resource (CORS diagnostic) and immediately specifies the exact exchange performed: an OPTIONS preflight plus a GET/HEAD with an Origin header. Among siblings like check_ssl, dns_lookup and trace_redirects, this is unambiguously the browser-CORS-evaluation tool.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: an agent can infer it is for determining whether a browser would permit a cross-origin request, but there is no explicit 'use this when' guidance and no contrast with sibling diagnostics (e.g. check_ssl or scan_security_headers). Adequate but clearly gapped.

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

All mcp-server 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