Skip to main content
Glama

Go-Live Check

analyze_headers

Read-onlyIdempotent

Check raw HTTP response headers from a deployment you already operate. Returns the same object as POST /v1/analyze. Unknown fields are ignored. A url field is not fetched. Nothing is stored. Nothing is for sale.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
platformNoPlatform whose config the caller can edit. A fix snippet is attached only for caddy, nginx, vercel, netlify, or nextjs. Any other declared platform, or an omitted platform, returns fix null. This server does not guess the platform from the Server header.
config_textNoOptional config text. Not copied into the response. When platform is caddy and this is non-empty, GLC-HSTS-MISSING includes config_header present or absent for one Caddy Strict-Transport-Security form with max-age greater than 0, GLC-CSP-MISSING includes config_header present or absent for one Caddy Content-Security-Policy form with a non-empty quoted value, GLC-NOSNIFF-MISSING includes config_header present or absent for one Caddy X-Content-Type-Options form set to nosniff, GLC-FRAME-MISSING includes config_header present or absent for one Caddy X-Frame-Options form set to DENY or SAMEORIGIN, GLC-REFERRER-MISSING includes config_header present or absent for one Caddy Referrer-Policy form with a non-empty value, and GLC-SERVER-VERSION-LEAK includes config_header present or absent only when that text deletes both Server and X-Powered-By. One deletion is absent. GLC-CORS-WILDCARD-CREDENTIALS includes config_header present or absent for one Caddy > replace of Access-Control-Allow-Origin whose replacement is non-empty and is not *. A line that sets that header without >, and a deletion, are absent. A Content-Security-Policy frame-ancestors line does not count as X-Frame-Options. When platform is nginx and this is non-empty, GLC-HSTS-MISSING includes config_header present or absent for one nginx add_header Strict-Transport-Security line with max-age greater than 0, GLC-CSP-MISSING includes config_header present or absent for one nginx add_header Content-Security-Policy line whose quoted value is non-empty after trim, and GLC-NOSNIFF-MISSING includes config_header present or absent for one nginx add_header X-Content-Type-Options line whose quoted value is nosniff. Any other value is absent. GLC-FRAME-MISSING includes config_header present or absent for one nginx add_header X-Frame-Options line whose quoted value is DENY or SAMEORIGIN. Any other value is absent. Content-Security-Policy-Report-Only does not count. A Content-Security-Policy frame-ancestors line does not count as X-Frame-Options. An empty quoted value, or a quoted value that is only spaces, is absent. A value that contains {, }, or $ is absent. GLC-REFERRER-MISSING includes config_header present or absent for one nginx add_header Referrer-Policy line whose quoted value is non-empty after trim. After trim, the accepted lines are add_header Referrer-Policy "<value>" always; and add_header Referrer-Policy "<value>";. The semicolon is required. An empty quoted value, or a quoted value that is only spaces, is absent. A value that contains {, }, or $ is absent. When platform is nginx, the version-leak field is present only for both lines server_tokens off; and proxy_hide_header X-Powered-By;. One of those lines is absent. The CORS field is present for one add_header Access-Control-Allow-Origin line whose quoted value is non-empty after trim and is not *. When platform is vercel, JSON headers entries are scanned for HSTS, CSP, nosniff, frame, referrer, and Access-Control-Allow-Origin using those same value rules, and the version-leak field is absent because vercel.json cannot delete Server or X-Powered-By. When platform is netlify, an indented Header: value line is scanned the same way, and the version-leak field is absent. When platform is nextjs, a headers() key and value pair is scanned the same way, and the version-leak field is present only when poweredByHeader is false. A value that contains {, }, or $ is absent. The Caddy scans still run only when platform is caddy. Other config text is not checked. Do not include secret values.
headers_rawYesRaw HTTP response headers from a deployment this agent already operates, including an optional status line, as curl -sI prints them. This server does not request a URL.
paths_testedNoOptional paths. Accepted and not checked. This server does not request them.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesYes
schemaYes
checkedYes
findingsYes
platformYes
config_textYes
paths_tested_countYes
parsed_header_countYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: unknown fields are ignored, no URL is fetched, nothing is stored, and the return shape matches POST /v1/analyze. It does not discuss auth or rate limits, so not a 5.

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?

Five short, front-loaded sentences with no bloat; the key scope constraint (you already operate the deployment) leads. 'Nothing is for sale' is an unusual note but it does carry meaning about no upsell/monetization.

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 a rich output schema and fully documented parameters, the description only needs to frame purpose and boundaries, which it does. The reference to 'the same object as POST /v1/analyze' presumes knowledge of a separate endpoint, a minor gap.

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% and the per-parameter descriptions are extremely detailed, so baseline is 3. The description only adds marginal clarification ('A url field is not fetched', 'Unknown fields are ignored') that lightly reinforces the headers_raw semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: checks raw HTTP response headers from a deployment the caller operates. That is clearly distinct from the sibling tools (explain_finding, get_fix, report_feedback), though the description never names or contrasts them explicitly.

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?

The phrase 'from a deployment you already operate' implies when the tool applies (you have the headers, you are not scanning third parties), but there is no explicit when-to-use/when-not guidance and no routing to alternatives among the siblings.

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.

Resources