Object Detector Skill

What this skill does

Object Detector finds the objects in an image, from people, cars and traffic lights to dogs, laptops and cups, and returns each one's label, a numeric confidence and its bounding box in pixels and as fractions of the image, plus a count per label. Filter by minimum confidence or by the labels you care about. You switch it on with a single toggle — no SDK and no endpoint wiring — and it answers over MCP or REST using the same key as every other skill.

See it work

A real response from the Object Detector Skill — exactly what your agent gets back when it makes the call.

vervekit · objectdetectortool call

{
  "image": "http://images.cocodataset.org/val2017/000000039769.jpg",
  "minConfidence": 0.5
}

result

imageWidth: 640
imageHeight: 480
objectCount: 5
counts: { … }
objects: [ 5 items ]
minConfidence: 0.5
labels: null

Run it with your own input. Live calls happen in your dashboard, on your key.

Ways to use it

One toggle, a new capability

Enable Object Detector and your app or agent can detect object on demand — no SDK, no endpoint wiring. It answers over MCP or REST using the same key as every other skill.

A tool agents call themselves

Over MCP, Object Detector appears to your model as the objectdetector tool it invokes whenever a task needs it — you don't write the glue, the agent reaches for it.

REST from any backend

Prefer to call it directly? Any language that can send a GET can hit Object Detector to detect object inline in your own server-side code.

Use it in your app

Once enabled, this skill is reachable two ways — pick whichever fits how you build. Both use the same key.

For AI agentsMCP

It appears to your model as a callable tool. No extra code — the agent invokes it when a task needs it.

objectdetector

For apps & backendsREST

Call it from your server with one request and your key. Node, Python, Go — anything that can send a GET.

GET /v1/objectdetector

Ask your agent

“Enable Object Detector and ask your agent to detect object.”
“Use the Object Detector skill for me.”

Object Detector Skill, answered

How to connect it over MCP or REST.

How do I add Object Detector to my app or agent?

Enable the Object Detector Skill on VerveKit, then reach it two ways with the same key: over MCP (it appears to your agent as the objectdetector tool) or over REST (call it from any backend). No SDK to install and no endpoint to wire.

MCP or REST — which should I use?

Both work off one key. Use MCP when an AI agent should decide when to detect object — the skill shows up as a callable tool. Use REST when your own server-side code should call it directly. Many apps use both.

Which agents and frameworks does it work with?

Any MCP client — Claude, Cursor, LangChain, and custom agents all speak the Model Context Protocol, so Object Detector appears as a standard tool with nothing skill-specific to integrate.

How many credits does a Object Detector call cost?

Each call costs 10 credits. Every skill rides the same key and the same connection, so enabling more skills doesn't add more integrations to manage.

Do I need to install anything?

No SDK and no endpoint wiring — enabling the skill is a toggle. You point your agent at the VerveKit MCP endpoint (or call REST) and Object Detector is available immediately.

Where does the data come from, and what shows on my bill?

VerveKit runs on APIVerve, our production data engine; Object Detector is one of 300+ skills on the same key. Invoices and card statements show APIVERVE.

One toggle, a new capability

A tool agents call themselves

REST from any backend

Object Detector Skill, answered

Other ways to use Object Detector

Give your software a way to act on the world.

Scaling in production?