Skip to main content
ModelTerms

Agents & Tools · intermediate

Model Context Protocol (MCP)

MCP is an open standard for connecting LLMs to external tools and data sources. It defines a JSON-RPC protocol so any client (Claude Desktop, Cursor, IDE plugins) can talk to any MCP server.

Explanation

Before MCP, each AI app implemented tool integrations one by one. MCP standardizes the contract: a server exposes tools, resources, and prompts via a uniform interface; any compliant client can plug in.

The ecosystem already includes MCP servers for filesystems, GitHub, Slack, Google Drive, browsers, and dozens of databases. The protocol covers transport (stdio, HTTP, SSE), capability negotiation, and structured responses.

Examples

  • Claude Desktop loading the Filesystem MCP server to read local files.
  • A CI agent using a GitHub MCP server to triage issues.

Frequently asked

What is Model Context Protocol?

MCP is an open standard for connecting LLMs to external tools and data sources. It defines a JSON-RPC protocol so any client (Claude Desktop, Cursor, IDE plugins) can talk to any MCP server.

What is an example of model context protocol?

Claude Desktop loading the Filesystem MCP server to read local files.

How is Model Context Protocol related to Tool Use?

Model Context Protocol and Tool Use are both agents & tools concepts. Tool use is when an LLM can call external functions — APIs, code interpreters, databases, web fetchers — and read their results. The mechanism that turns chat into action.

Is Model Context Protocol considered intermediate?

Model Context Protocol is generally considered intermediate-level material in the AI and LLM space.

Tool UseAgents & Tools

Tool use is when an LLM can call external functions — APIs, code interpreters, databases, web fetchers — and read their results. The mechanism that turns chat into action.

Function CallingAgents & Tools

Function calling is the specific API mechanism by which an LLM emits a structured request to invoke a named function with typed arguments. The OpenAI-popularized way to do tool use.

AgentAgents & Tools

An AI agent is an LLM-driven system that decides which actions to take, executes them via tools, observes the results, and iterates until a goal is met.

MCP ServerAgents & Tools

An MCP server exposes tools, resources, or prompts via the Model Context Protocol so any compliant client (Claude Desktop, Cursor, IDE plugins) can call them without bespoke integration.

Agentic CodingAgents & Tools

Agentic coding is an LLM-driven workflow where the model reads code, plans changes, edits files, runs commands, and iterates against feedback — autonomously closing tasks rather than just suggesting code.

Side-by-side comparisons

Sources