RunStack Checks

HTTP response inspection

check_http

Read-onlyIdempotent

Request a public URL from outside your network and inspect the HTTP layer: status code, full redirect chain, security headers (HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy…), caching and compression headers. Use to debug redirect loops, unexpected status codes or missing headers as real visitors and CDNs see them, or to verify a web server / CDN config change after deploy. Use check_tls instead for certificate or TLS protocol questions. Returns a verdict and findings with fixes.

Input Schema

Name	Required	Description	Default
`url`	Yes	Full public http(s) URL, e.g. https://example.com/login
`followRedirects`	No	Follow redirects and report every hop (default true). Set false to see only the first response.

Output Schema

Name	Required	Description
`ok`	Yes	false when the check could not run (see error / message)
`tool`	No
`error`	No	Error code when ok is false
`facts`	No
`notice`	No	Usage note, e.g. anonymous-tier limits
`target`	No	What was checked
`message`	No
`verdict`	No
`findings`	No
`headline`	No	One-line summary
`reportUrl`	No	Shareable report link

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

addedOutput schema / properties / notice

Added value: +{
+  "description": "Usage note, e.g. anonymous-tier limits",
+  "type": "string"
+}

Changed5 schema fields changedOct 18, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / followRedirects / default
```
Added value: +true
```

changedInput schema / properties / followRedirects / description

Previous value: -"Follow redirects (default true)"New value: +"Follow redirects and report every hop (default true). Set false to see only the first response."

changedInput schema / properties / url / description

Previous value: -"Public http(s) URL"New value: +"Full public http(s) URL, e.g. https://example.com/login"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "error": {
+      "description": "Error code when ok is false",
+      "type": "string"
+    },
+    "facts": {
+      "items": {
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "value": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "label",
+          "value"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "findings": {
+      "items": {
+        "properties": {
+          "code": {
+            "type": "string"
+          },
+          "detail": {
+            "description": "Why it matters / cause",
+            "type": "string"
+          },
+          "docs": {
+            "description": "How-to article URL",
+            "type": "string"
+          },
+          "fix": {
+            "description": "How to fix",
+            "type": "string"
+          },
+          "severity": {
+            "enum": [
+              "error",
+              "warning",
+              "info",
+              "ok"
+            ],
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "severity",
+          "title"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "headline": {
+      "description": "One-line summary",
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "ok": {
+      "description": "false when the check could not run (see error / message)",
+      "type": "boolean"
+    },
+    "reportUrl": {
+      "description": "Shareable report link",
+      "type": "string"
+    },
+    "target": {
+      "description": "What was checked",
+      "type": "string"
+    },
+    "tool": {
+      "type": "string"
+    },
+    "verdict": {
+      "enum": [
+        "ok",
+        "warn",
+        "fail"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedOct 17, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld). The description adds real behavioral context beyond them: the request originates 'from outside your network' so results reflect what 'real visitors and CDNs see', which tells the agent why this vantage point matters. It also notes the return is a verdict plus findings with fixes, though it does not discuss rate limits or failure modes.

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 the action and inspection scope, then usage, then the sibling exclusion, then the return shape. Dense but each sentence carries information; the header enumeration is slightly list-heavy but justified by the tool's scope.

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 and annotations carry the safety profile, so the description need not explain return values; it still summarizes them. With 100% param coverage and clear routing to check_tls, an agent has everything needed to select and invoke this tool correctly.

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 coverage is 100%, so both parameters (url and followRedirects) are already fully documented with defaults and examples. The description adds no additional parameter syntax or format detail beyond what the schema provides, so the baseline of 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?

Specific verb+resource ('Request a public URL ... inspect the HTTP layer') with an explicit enumeration of what is inspected: status code, redirect chain, security headers, caching/compression headers. It also names the sibling it is not (check_tls), so an agent can separate it from the other check_* tools without opening schemas.

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 scenarios (debug redirect loops, unexpected status codes, missing headers, verify a CDN/server config change after deploy) and an explicit alternative with its selecting condition ('Use check_tls instead for certificate or TLS protocol questions').

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

All RunStack Checks tools Inspect

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.