User Agent Parser Skill

Overview

A user agent and device detection API. User Agent Parser works by analyzing the user agent string provided and extracting information about the browser, operating system, and device. It uses advanced algorithms to parse the user agent string and return the information in a structured format.

Live Test User Agent Parser Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as UserAgentParserSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "UserAgentParserSkill",
  "arguments": {
    "ua": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
  }
}

You do not name the tool yourself; the model picks it. Asking about Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 in the terms this skill covers is enough for it to reach for UserAgentParserSkill on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`ua`Required	string	The user agent string to parse

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "ua": "Mozilla/5.0 (Windows NT 6.4) AppleWebKit/537.36.0 (KHTML, like Gecko) Chrome/60.0.0.0 Safari/537.36.0",
    "browser": {
      "name": "Chrome",
      "version": "60.0.0.0",
      "major": "60"
    },
    "engine": {
      "name": "Blink",
      "version": "60.0.0.0"
    },
    "os": {
      "name": "Windows",
      "version": "10"
    },
    "device": {},
    "cpu": {},
    "isMobile": false,
    "isBot": false,
    "deviceType": "desktop",
    "summary": "Chrome 60 on Windows 10"
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`ua`	string	`Mozilla/5.0 (Windows NT 6.4) AppleWebKit/537.36.0 (KHTML, like Gecko) Chrome/60.0.0.0 Safari/537.36.0`	The original user agent string that was parsed
`browser`	object	`{…}`	Browser detected in the user agent; empty when none is recognised
`browser.name`	string	`Chrome`	Name of the browser (e.g., Chrome, Firefox, Safari)
`browser.version`	string	`60.0.0.0`	Full version of the browser (e.g., 60.0.0.0)
`browser.major`Premium	string	`60`	Major version number of the browser
`engine`	object	`{…}`	Rendering engine detected in the user agent
`engine.name`Premium	string	`Blink`	Name of the rendering engine (e.g., Blink, WebKit)
`engine.version`Premium	string	`60.0.0.0`	Version of the rendering engine
`os`	object	`{…}`	Operating system detected in the user agent
`os.name`	string	`Windows`	Operating system name (e.g., Windows, macOS, Linux)
`os.version`	string	`10`	Version of the operating system
`device`	object	`{…}`	Device information object (type, vendor, model)
`cpu`	object	`{…}`	CPU architecture information (architecture type and details)
`isMobile`	boolean	`false`	Whether the user agent is from a mobile device
`isBot`	boolean	`false`	Whether the user agent appears to be a bot/crawler
`deviceType`	string	`desktop`	Device class: desktop, mobile, tablet, console, smarttv, wearable, embedded, xr or bot; null when it can't be determined
`summary`Premium	string	`Chrome 60 on Windows 10`	Human-readable summary of browser and OS

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This skill is not part of VerveKit. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Adaptive Asset Delivery: Web servers inspect the device type and mobile flag to serve lightweight media assets and alternate layouts to smartphones and tablets.
Crawler Traffic Segregation: When incoming requests arrive, API gateways read the bot flag to filter out search engine spiders and scrapers from application metrics.
Compatibility Banner Triggers: Flag outdated client environments before pages fail by evaluating the reported browser version against required feature sets.
Platform Installer Matching: To route downloads accurately, software distribution sites match the visitor's operating system and CPU architecture directly to the right installer package.

Other ways to use User Agent Parser Skill

Set up User Agent Parser Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →