Blog/What is Model Context Protocol (MCP)?
Definition

What is Model Context Protocol (MCP)?

By Samuel Seidel · Published September 9, 2026

Model Context Protocol (MCP) is an open specification, published by Anthropic, for connecting an LLM application to external tools, files and data sources through one standard interface. Instead of writing a custom integration for every tool, a developer runs or connects to an MCP server that exposes those tools in a consistent format, and any MCP-compatible client can discover and use them.

The problem it addresses

Before a standard existed, connecting a model to a database, a file system, or a third-party API meant writing bespoke glue code for each combination of model and tool. An assistant that needed to read local files, query a database, and call a search API required three separate integrations, each tied to whichever model framework was in use. MCP separates serving tools from calling the model: a server implements the protocol once, and any MCP client can use it, whichever model sits behind that client.

How it's structured

MCP defines a client-server relationship. An MCP server exposes three main things: tools the model can invoke (functions with defined inputs and outputs), resources it can read (files, records, or other data), and prompt templates it can reuse. An MCP client, typically embedded in an application like an IDE or chat interface, connects to one or more servers, lists what they offer, and passes that information to the model so it can decide when to use them. The connection can run locally over standard input and output, or remotely over HTTP.

How MCP relates to function calling

MCP builds on top of function calling rather than replacing it. Function calling is what lets a model output a structured request to invoke a named function with specific arguments. MCP standardizes the layer above that: how a client discovers which functions are available in the first place, how it presents them to the model, and how results get passed back, so that adding a new tool doesn't require reworking the model integration itself.

Where things still vary

MCP is a young specification. Several model providers and tool vendors have published servers and clients, but supported features, authentication handling and versioning differ between implementations. Before relying on advanced features such as streaming resource updates or server-initiated prompts, check the current spec and your client's support, since these have changed during the protocol's early revisions.

Why it matters for self-hosted deployments

MCP doesn't depend on where the model runs. A self-hosted model behind an OpenAI-compatible API can sit behind an MCP client the same way a hosted API would, calling internal MCP servers that reach your databases, ticketing systems or file shares. If you already keep inference on your own hardware for data-residency reasons, running the tool layer through internal MCP servers keeps the tool calls inside your network too. See what is an LLM agent for how tool access fits into agent design more broadly.

Related pages

First top-up: pay $20, get $30 in credit

Run tool-calling workloads on a dedicated node.

One dedicated Spark, $0.79/hour, deployed in minutes in Europe, North America or East Asia.

Create account