Author

aiterms

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard that lets AI apps connect to external tools, data sources, and workflows through a common interface, usually via an MCP client talking to an MCP server.

Why it matters

Without a shared protocol, every AI app tends to build one-off integrations for files, databases, APIs, and internal tools. MCP solves that by giving model-powered applications a standard way to discover and use capabilities from different systems.

In practice, you reach for MCP when you want:

• one assistant app to work with many tools,
• one tool integration to be reusable across multiple LLM apps,
• a cleaner boundary between the model and the systems it can access.

It is especially useful when you want model context to be assembled dynamically from external sources instead of hardcoding every connector inside the app.

How it works

At a high level, an MCP client is the AI application or host that wants access to tools or data. An MCP server exposes those capabilities in a standardized way.

The client first connects to the server and discovers what it offers. In MCP, those offerings are commonly grouped into a few kinds of capabilities, such as:

• tools: actions the model can request, like “search tickets” or “create draft,”
• resources: data the client can read, like files or records,
• prompts: reusable prompt templates or instructions.

The protocol defines how the client asks what is available and how it invokes those capabilities. The point is not to make the model “smarter” by itself, but to give it a predictable way to reach outside the prompt and use external context safely and consistently.

A useful mental model: MCP is to AI integrations what a standard plug is to devices. The device still does the work; the plug just makes the connection consistent.

Tiny concrete example

Suppose your coding assistant needs access to a GitHub issue tracker.

• The assistant app acts as the MCP client.
• A small service exposes GitHub issue search as an MCP server.
• The assistant asks the server what tools it has.
• The server replies with something like “search issues” and “get issue details.”
• The assistant calls “search issues” with a query like repo:acme/payments bug login timeout.

The model then uses the returned issue data in its answer instead of relying only on what was already in the chat.

Common pitfalls / when NOT to use it

• Not a replacement for your app backend. MCP standardizes model-to-tool access; it does not replace business logic, auth design, or data modeling.
• Not needed for simple prompts. If the model only needs static instructions, MCP is overkill.
• Do not expose unsafe tools casually. A standard protocol does not make a dangerous action safe. You still need authorization, scoping, logging, and human review where appropriate.
• Don’t assume every integration should be an MCP server. If only one app will ever use a connector, a direct API integration may be simpler.
• Watch the trust boundary. The model may request actions you did not intend; server-side enforcement matters more than prompt wording.

Related terms

• LLM tool use
• Function calling
• Agent
• RAG

Related terms

• What is function calling?
• What is an MCP server?
• What is a tool schema / tool definition?
• What is a JSON schema for tool arguments?
• What is parallel tool calling?
• What is tool result / tool message?
• What is a computer-use / browser-use tool?
• What is a code execution tool (sandbox)?

同じ著者の記事

What is chunking (and semantic chunking)?

Chunking is the practice of splitting a larger piece of text or data into smaller pieces so a system can process, store, or retrieve it more effectively; semantic chunking does the same thing, but tries to cut at meaningful boundaries instead of by fixed length. Chunking is a core technique in retrieval-augmented generation (RAG), document search, summarization, and any workflow that needs to feed long content into an LLM. Why teams use it: LLMs have context limits, so very large documents must

papoo.work

What is semantic search?

Semantic search is a way to find information by meaning, not just by matching the exact words you typed. Traditional keyword search is good when you know the exact term to look for. Semantic search helps when users phrase the same idea in different words, use synonyms, or ask a question instead of naming a document. You’d reach for it when: search queries are messy or conversational, exact wording varies a lot across documents, you want to retrieve “about the same thing” rather than “contains th

papoo.work

What is an embedding?

An embedding is a vector embedding: a list of numbers that represents something—like a word, sentence, image, or user—in a way a model can compare mathematically. Embeddings turn messy, human data into a form machines can use for: Similarity search: “Find documents like this one.” Recommendations: “Show items close to what the user liked.” Clustering and classification: “Group related things together.” Retrieval for LLMs: “Fetch the most relevant context before generating an

papoo.work

What is a vector database?

A vector database, also called a vector store, is a system for storing and searching data by its numerical embeddings so you can find items that are “most similar” rather than exactly matching text or IDs. Regular databases are great when you know the exact thing you want: a user ID, a product SKU, a timestamp range. But many AI features need semantic search or nearest-neighbor retrieval: “find questions like this one,” “retrieve passages relevant to this prompt,” or “recommend items

papoo.work

What is retrieval-augmented generation (RAG)?

Retrieval-augmented generation, or RAG, is a way to make a language model answer questions using relevant external documents it retrieves first, instead of relying only on what it memorized during training. RAG helps when you want answers that are: grounded in your own content, such as docs, policies, tickets, or product knowledge easier to update than retraining a model more likely to mention current or proprietary information In practice, teams reach for RAG when a model needs to answer “what

papoo.work

What is tool use in AI agents?

Tool use in AI agents is when an LLM-based agent can call external functions, APIs, or programs—often called a tool calling agent—to get information or take actions it cannot do reliably from text alone. A plain language model is good at generating text, but it does not reliably know live facts, cannot directly query a database, and should not guess at actions like sending email or creating tickets. Tool use solves that by letting the model delegate specific steps to purpose-built systems. Y

papoo.work

What is the agent loop (perceive-plan-act)?

The agent loop, also called the perceive-plan-act loop, is the repeated cycle where an AI agent observes its situation, decides what to do next, and then takes an action. This is the basic control pattern behind many agentic systems. Instead of asking a model for one one-off answer, you let it keep checking the world, updating its plan, and acting until the task is done or it should stop. You reach for it when the task is dynamic, multi-step, or depends on intermediate results: calling tools, br

papoo.work

What is a ReAct agent?

A ReAct agent is an LLM-driven system that alternates between reasoning and acting—often called reason + act or ReAct prompting—so it can decide what to do next, use tools, and update its plan from the results. ReAct is useful when a model should not just produce an answer, but also take steps in the world: search a document set, call an API, inspect a database, or ask for more information. In practice, teams reach for it when: a plain chat completion is too static, the task

papoo.work

What is an agentic workflow?

An agentic workflow is a workflow where an AI system can decide and take multi-step actions toward a goal, instead of only producing a one-shot answer; you may also hear this called an agentic system. Use an agentic workflow when the task is not just “generate text,” but “figure out what to do next.” That includes tasks like investigating an issue, pulling together information from multiple tools, retrying after failure, or following conditional branches based on intermediate results

papoo.work

What is an AI agent?

An AI agent, also called an LLM agent or autonomous agent, is a system that can pursue a goal by deciding what to do next, taking actions, and using the results to keep going. Most AI systems just answer a prompt once. An agent is useful when one answer is not enough and the system needs to act over multiple steps: search, call tools, inspect results, retry, and stop when the goal is met. You’d reach for an agent when the task is: open-ended, not a single fixed response dependent on external

papoo.work