MCP — Model Context Protocol
The Model Context Protocol is an open standard for connecting AI systems to external data sources and tools. It defines a common way to expose what can be read and what can be run, so one connection serves different assistants instead of writing a bespoke integration for each.
What is Model Context Protocol?
The Model Context Protocol is an open standard for connecting AI systems to external data sources and tools. It defines a common way to expose what can be read and what can be run, so one connection serves different assistants instead of writing a bespoke integration for each.
Also: MCP
Why it matters
What changes in a SaaS
It solves a multiplication problem: without a standard, connecting N tools to M assistants is N times M integrations, all different and all to maintain. With a common protocol each tool is exposed once. For a buyer it means the connection you build today is not thrown away when you change AI vendor.
Model Context Protocol in detail
What an MCP server exposes
Three things: resources, which are data that can be read; tools, which are actions that can be run; and prompts, which are interaction templates. Keeping reads and runs separate is what lets you grant permissions with judgement.
What changes in practice
Exposing your product to an AI assistant stops being a per-vendor project. Publish an MCP server and any compatible client can query it with the permissions you define.
What it does not solve
Deciding what to expose and with what permissions, which is still yours and still the part that matters. A protocol standardises the how, not the what.
How Intake handles it
Questions about Model Context Protocol
What does MCP stand for?
Model Context Protocol: an open standard for connecting AI systems to external data and tools so the same connection works across assistants.
Are MCP and tool calling the same thing?
No. Tool calling is a model asking for a function to be run; MCP is a standard for how those functions are described and exposed so they work in more than one place.
Related terms
A term on its own is only half understood. These come up in the same conversation.
Tool calling
Tool calling is the mechanism by which a language model can run functions you define instead of only writing. You describe the available tools, the model decides which one to use and with what arguments, and it receives the result to fold into its answer.
AI agent
An AI agent is a system that, beyond generating text, reads data and takes actions to finish a task. In support that means it checks the actual state of the customer account before answering, and when the answer involves doing something, it does it instead of explaining how.
LLM — Language model
A language model is a system trained on enormous amounts of text that, given a fragment, predicts how it continues. Writing, summarising, translating and holding a conversation all come out of that one simple capability: they are all ways of continuing a text plausibly.
Hallucination
A hallucination is an answer from a language model that sounds right and is not: an invented figure, a feature that does not exist, a plausible number nobody checked. It is not a bug, it is a direct consequence of how a model works — it produces the most probable continuation, not the verified one.
Context window
The context window is everything a language model can have in front of it at once to produce an answer: the system instruction, the conversation history, the passages retrieved from documentation and the data looked up. It is measured in tokens and it has a ceiling.
System prompt
The system prompt is the fixed set of instructions a model receives before every conversation: who it is, what it can and cannot do, what tone it answers in and what to do when it does not know something. The user never sees it and it is sent on every request.
