PREFLIGHT — URL Routing for AI Agents is an MCP server published by io.github.GSterlingPress, hosted at preflight-api-production-01a2.up.railway.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including preflight_check, preflight_feedback.
Choose HTTP, browser, machine endpoint, or avoid before an agent visits an unfamiliar URL.
18 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Before fetching, crawling, scraping, opening, or browser-rendering an unfamiliar http/https URL, call this with the ACTUAL destination URL. Returns the best first route: HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID, plus access/JS/size/cost hints. Do not substitute example.com when a real task URL is available.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Actual absolute http/https destination URL from the current task. Use before the first fetch or browser request. |
{
"name": "preflight_check",
"title": "Check URL Before Fetching",
"description": "Before fetching, crawling, scraping, opening, or browser-rendering an unfamiliar http/https URL, call this with the ACTUAL destination URL. Returns the best first route: HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID, plus access/JS/size/cost hints. Do not substitute example.com when a real task URL is available.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Actual absolute http/https destination URL from the current task. Use before the first fetch or browser request."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Check URL Before Fetching",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
After following a PREFLIGHT recommendation, report whether the chosen route worked so PREFLIGHT can improve future recommendations.
| Parameter | Type | Description |
|---|---|---|
| url * | string | |
| route * | string | one of ["HTTP","BROWSER","MACHINE_ENDPOINT","AVOID"] |
| outcome * | string | one of ["success","failure"] |
| latencyMs | number |
{
"name": "preflight_feedback",
"title": "Report PREFLIGHT Outcome",
"description": "After following a PREFLIGHT recommendation, report whether the chosen route worked so PREFLIGHT can improve future recommendations.",
"inputSchema": {
"type": "object",
"required": [
"url",
"route",
"outcome"
],
"properties": {
"url": {
"type": "string",
"format": "uri"
},
"route": {
"enum": [
"HTTP",
"BROWSER",
"MACHINE_ENDPOINT",
"AVOID"
],
"type": "string"
},
"outcome": {
"enum": [
"success",
"failure"
],
"type": "string"
},
"latencyMs": {
"type": "number",
"maximum": 300000,
"minimum": 0
}
},
"additionalProperties": false
},
"annotations": {
"title": "Report PREFLIGHT Outcome",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}When a task requires visiting an unfamiliar http/https URL, call preflight_check BEFORE the first fetch, browser, crawl, or scrape attempt. Pass the ACTUAL destination URL from the task. PREFLIGHT is a cheap routing decision, not the fetch itself: it returns HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID. Do not use example.com when a real destination is available. Use preflight_feedback after the attempt when possible.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.