What is MCP (Model Context Protocol)?

MCP, the Model Context Protocol, is an open protocol that gives AI assistants and agents a standard way to use external tools and data. A small program called an MCP server exposes functions, and the assistant calls them while it works on a request.

How it works

Anthropic announced MCP as a standardized way for AI models to interact with external tools. The idea is plain. An MCP server is a small program that exposes functions, and each server describes what it can do with a simple schema. Enable a filesystem server and the assistant gets functions such as read_file and write_file. Enable a server for a database and it can query that database.

Nothing in it is exotic. The messages are JSON-RPC, a pattern used for decades, over a local connection when the server runs on your machine. A server can also be deployed remotely over HTTP, and then it has to implement the authorization the protocol requires. Servers compose: one request can use several of them in sequence. The person or the team that operates the assistant decides which servers are enabled and what each one may reach.

Where it shows up in real work

I built Airtable MCP, an open-source server that connects Airtable bases to assistants such as Claude. It began with a small annoyance. I was restructuring database schemas and kept copying schema information between the API documentation and my project. With the server in place I asked in plain language for the feature requests with the most votes, or for the number of bug reports still open. The hardest bug was authentication. The server connected to Airtable in my tests and failed when Claude used it, because of the way the token was passed through the MCP pipeline.

What it is not

MCP is not a security layer. It provides the interface between the agent and an operation, and database permissions, application authorization and operational controls still have to enforce the boundary. It is also not a way to give a password to a model: the model receives a tool definition and the minimum result it needs to answer, and the credentials stay in the secret facility of the runtime.

When you need it

Use MCP when an assistant or an agent should work with a system directly and people are still copying data in and out of a chat window. For company data, begin with specific read tools, such as one that returns the status of an order, and define their inputs, returned fields and failure behavior. A general SQL tool needs a much stronger design for isolation and query control. An instruction that asks the model to behave is not enough.

Work and evidence

Airtable MCP (opens in a new tab)

My contribution: Built an open-source MCP integration for querying and editing Airtable bases.

What this supports: A concrete database-to-agent integration with a linked public repository.

What it does not establish: An integration example, not evidence that arbitrary corporate databases or tenant policies are secured by default.

Source reviewed:

Common questions

What is an MCP server?

A small program that exposes functions to an AI assistant or agent and declares them with a schema. A filesystem server offers functions such as read_file and write_file, and an email server offers send_email and read_inbox. The assistant decides when to call them during the conversation.

Is MCP secure?

The protocol alone does not secure anything. It provides the interface, and the boundary is enforced by database grants, application authorization and operational controls. The caller and the tenant must come from trusted authentication context, never from an identifier that the model supplies.

Which AI assistants can use an MCP server?

Clients that support the protocol. The setup notes of my Airtable server name Claude Desktop, Cursor, Cline and Zed. The server is installed once and the assistant is restarted.

Can an assistant change data through MCP, or only read it?

Both are possible. With my Airtable server I asked questions and also updated the status of a record. For company data I separate reading from changing state: a proposed write passes schema validation, business rules and authorization before it runs, and a consequential operation needs an approval bound to the exact operation and its arguments.

Open to senior AI engineering roles and contract engagements, remote in the US, Mexico and Latin America.