MCP (Model Context Protocol)
An open protocol for plugging tools and data into AI apps: write a server once, use it from any client.
An MCP server exposes tools, resources and prompts over a standard protocol. Clients such as Claude, ChatGPT, IDEs and coding agents connect to it and offer those tools to the model. For a product, an MCP server is the way to become usable by agents without each vendor building its own integration.
Related terms
- Tool use (function calling): The model returns a structured request to run a function you defined; your code runs it.
- AI agent: A model that decides its next step itself, calls tools and repeats until the task is done.
- Prompt injection: Instructions hidden in data (a web page, an email, a file) that the model follows as if they came from you.
- Tool poisoning (MCP): An attack that hides instructions in a tool’s name, description or output, so an agent using that tool follows the attacker instead of the user.
- A2A (Agent2Agent protocol): An open protocol for one AI agent to hand a task to another agent, possibly from another vendor, and follow it until it is done.
