Model Context Protocol (MCP)
Also known as: MCP
An open standard from Anthropic for connecting LLMs to external tools and data sources through a uniform server interface.
The Model Context Protocol (MCP) is an open spec that lets any LLM client connect to any tool server through a single, well-defined interface. Instead of writing bespoke integrations for every model, a developer publishes an MCP server (for GitHub, Postgres, Slack, your own API) and every MCP-aware client — Claude Desktop, Cursor, Cline, ChatGPT desktop — can use it.
MCP standardises three primitives: tools (functions the LLM can call), resources (read-only context the LLM can fetch) and prompts (reusable templates). It is becoming the de-facto plug-in system for agentic AI in 2026.
Related terms
- AI Agent
An LLM-based system that can plan, use tools and take multi-step actions toward a goal — not just answer a single prompt.
- Agentic AI
AI systems that act autonomously over many steps to achieve a goal, combining planning, tool use and memory.
- Large Language Model (LLM)
A neural network trained on massive text corpora to predict the next token, used for chat, coding, reasoning and as the brain inside AI agents.
More to explore
Other wiki entries that touch on Model Context Protocol (MCP).
- Tokens
The atomic units that LLMs read and write — sub-word pieces produced by a tokenizer. Pricing and context limits are measured in tokens, not words.
- Context Window
The maximum number of tokens an LLM can read in a single request, including the prompt, retrieved documents and the model's own reply.
- Prompt Engineering
The practice of designing inputs to LLMs to reliably produce useful outputs — through structure, examples, role-setting and constraints.