What is MCP (Model Context Protocol)?
The working definition
MCP is an open protocol that lets an AI application discover and call external tools and data sources through one standard interface instead of a custom integration per model.
Anthropic published it as an open standard in November 2024 and handed stewardship to the Agentic AI Foundation in December 2025, so it is now governed as a vendor-neutral spec. The practical effect: a connector you write once can be used by any client that speaks the protocol.
The problem it solves
Before a shared protocol, every combination of model and tool was its own integration. Five models and eight internal systems is forty pieces of glue, each with its own auth handling, schema, and error semantics, all of it rewritten when you switch providers.
MCP collapses that into eight servers and five clients. The integration count stops multiplying, and the tooling stops being hostage to the model you happened to start with.
How it works
Hosts, clients, and servers
The host is the AI application the person is using. It runs clients, and each client holds a connection to one server. A server exposes a specific capability: a database, a file store, a ticketing system, an internal API.
What a server exposes
- Tools: actions the model can invoke, with typed inputs and a described effect.
- Resources: data the application can read into context, such as files, records, or documents.
- Prompts: reusable, parameterized templates the server offers for common tasks.
Discovery
The client asks the server what it offers rather than having the list hard-coded. Adding a capability to the server makes it available to every connected client without shipping a new build of the assistant. For finding servers in the first place, the official MCP Registry launched in September 2025 as a shared catalogue of published servers.
Transports
Local servers run over stdio. Remote servers use Streamable HTTP, which replaced the original HTTP-plus-SSE transport in the 2025-03-26 spec revision and is what current clients expect. Remote servers authorize with OAuth 2.1: the server acts as a resource server, delegates to an identity provider, and issues tokens scoped to that resource rather than accepting a shared static key.
When to use MCP, and when not to
Use it when
- More than one AI client needs the same capability.
- You expect to change models and want the tooling to survive the change.
- You want capabilities discoverable at runtime rather than baked into a prompt.
- An off-the-shelf server already exists for the system you are connecting.
Skip it when
One application calls one internal service on a fixed path. A direct function call is simpler, faster, and easier to reason about. A protocol you added for elegance rather than need is still a dependency you now maintain.
Security is the part people skip
An MCP server is a permission surface. Connecting one hands a model the ability to act inside a system on your behalf, so treat it with the seriousness of any other integration credential.
- Scope every server to the narrowest set of actions the job needs. Read-only unless writing is the point.
- Treat tool output as untrusted input. Content returned by a tool can carry instructions aimed at the model, and prompt injection through tool responses is a live attack path.
- Keep irreversible actions behind human approval no matter how reliable the loop has been.
- Log every tool call with its arguments so an unexpected outcome can be traced rather than guessed at.
- Vet third-party servers before installing them, the same way you would vet any dependency with credentials attached.
What is the Model Context Protocol?+
MCP is an open standard for connecting AI applications to external tools and data sources through one consistent interface, so a connector written once works with any client that supports the protocol.
Who created MCP?+
Anthropic released MCP as an open standard in November 2024 and donated it to the vendor-neutral Agentic AI Foundation in December 2025, which now maintains the specification.
What problem does MCP solve?+
It removes the need for a custom integration for every combination of model and tool. Instead of rewriting glue code when you change providers, you keep the servers and swap the client.
Is MCP the same as an API?+
No. An API is the underlying service. MCP is a standard wrapper that describes that service to a model, including which tools exist, what arguments they take, and what data can be read.
Is MCP secure?+
The protocol does not make an integration safe by itself. Scope servers narrowly, treat tool output as untrusted input because prompt injection can arrive through it, gate irreversible actions behind human approval, and log every call.
Need your internal systems reachable by any model you run?
Bring us your project →