What is MCP?

MCP — the Model Context Protocol — is an open standard for connecting AI models to tools and data. It's the difference between an app you wire up by hand and an agent that reaches for the right capability on its own. Here's what it is, how it differs from a REST API, and why it matters.

  • Open standard
  • Built for agents
  • Powers VerveKit
The idea

A shared language between models and the real world

Strip away the acronym and MCP is three simple ideas.

A protocol, not an API

MCP is a shared language for how an AI model talks to tools and data. Instead of a bespoke integration per service, every MCP-speaking client and server understands the same handshake — like USB-C for AI context.

  • Open standard
  • Client ⇄ server

Tools the model can call

An MCP server advertises its capabilities as tools, each with a model-readable name, a description, and a schema. The model reads that catalog and decides — on its own — which tool to call and with what arguments.

  • Self-describing
  • Model-driven

Live context, on demand

Rather than hoping a fact sits in the model's training data, the agent calls a tool at answer time and gets a fresh, real result back. MCP is how a model reaches past its cutoff into the real world.

  • Real-time
  • No fine-tuning
MCP vs REST

Not a replacement — a different consumer

The most common question, answered: how MCP relates to the REST APIs you already know.

REST is for your code

A REST API gives your program an endpoint to call. You read the docs, wire up auth, model the response, and write the code that decides when to call it. The intelligence lives in what you build around it.

  • You wire it
  • You decide when

MCP is for the model

MCP hands the model a menu of tools it can understand and invoke without you writing per-call glue. The model chooses which tool fits the moment. Same data underneath — a different consumer.

  • Model wires it
  • Model decides when

You'll often want both

Agent features connect over MCP; your backend and scheduled jobs call the same capabilities over REST. VerveKit exposes every skill both ways, behind one key — so you're never forced to pick.

  • One key
  • MCP + REST
In practice

How VerveKit uses MCP

You don't build the server or wrap the tools — you connect and the skills show up.

  1. 01

    Grab one VerveKit key

    Sign up and get a single key. It covers all 350+ skills — no per-service accounts, no separate credentials to manage.

  2. 02

    Point your client at the MCP endpoint

    Add one server entry to Cursor, Claude Desktop, Cline, or any MCP client. Authorize once with OAuth — there's no key to paste into a config file.

  3. 03

    The skills appear as tools

    Every skill you enable shows up in the client as a native tool, with a name and description the model already understands. Nothing to register by hand.

  4. 04

    The agent calls what it needs

    Ask a question that needs live data and the model reaches for the right skill on its own — weather, currency, DNS, news — and answers from a fresh, real result.

Key terms

The words you'll see

The small vocabulary that comes with MCP.

MCP server

A program that exposes tools and data to models over MCP. VerveKit runs one for you, backed by 350+ skills — so you don't have to build or host it.

Tool

A single capability the model can invoke, with a name, description, and input schema. In VerveKit, each skill is a tool.

Tool call

The moment a model decides to invoke a tool and passes it arguments. The result comes back into the conversation for the model to use.

MCP client

The app the model runs inside — Cursor, Claude Desktop, or your own agent — that connects to MCP servers and surfaces their tools to the model.

MCP, answered.

The questions people ask when they first meet the protocol.

Read the docs
Is MCP the same as an API?
No — they solve different halves of the same problem. An API is an endpoint your code calls; you write the logic that decides when. MCP is a standard way to hand a model a set of tools it can understand and call by itself. The data underneath can be identical; MCP is about letting the model be the one reaching for it.
Who created MCP?
MCP (the Model Context Protocol) is an open standard introduced by Anthropic in late 2024 and adopted across the AI ecosystem. Because it's open, any client or server that speaks MCP can interoperate — which is exactly why VerveKit exposes its skills over it.
Do I need MCP to use VerveKit?
No. If you're building an agent, MCP is the smoothest path — every skill becomes a callable tool. If you're building a normal app or backend, call the same skills over REST with the same key. Most teams use both.
How do I connect VerveKit over MCP?
Point your MCP client at one endpoint and authorize with OAuth — no key to paste. See the MCP setup guides or the MCP Server overview for the exact steps.
What can an agent actually do with it?
Anything a skill covers — check the weather for a city, convert a currency, resolve a domain, pull the latest news, look up a timezone. The model calls the skill when a question needs a live fact, and answers from the real result instead of guessing.

Give your agent live tools.

Ready to connect?

Point your MCP client at one endpoint and every enabled skill becomes a callable tool.

See how it connects