Model Context Protocol (MCP)

Full definition

MCP defines two roles: clients (AI apps like Claude Desktop, IDEs, agent frameworks) and servers (wrappers around tools, databases, APIs, file systems). Servers expose tools, resources, and prompts; clients discover and invoke them over stdio or Streamable HTTP, which replaced the original HTTP+SSE transport in the March 2025 revision of the spec. By December 2025 MCP had been adopted by ChatGPT, Cursor, Gemini, Microsoft Copilot and Visual Studio Code, with more than 10,000 active public servers (Anthropic, 9 December 2025). MCP standardizes what previously required bespoke per-app integrations.

Why it matters

MCP turns tool integration from N×M to N+M — every MCP-compliant model can use every MCP server. For enterprises, this dramatically lowers the cost of connecting agents to internal systems and reduces vendor lock-in.

Example

A consulting firm exposes its CRM, file system, and time-tracking tools as three MCP servers; Claude, Cursor, and an internal LangGraph agent all consume the same servers without bespoke integrations.

Next steps

• Get a free workflow map →We map one of your workflows and give you a written verdict: software, a process change or AI. No obligation.
• AI consulting cost guide →Hourly rates and project budgets by firm tier, from independents to the Big Four.

Related terms

• Function Calling
  Function calling is an LLM capability where the model — given a schema of available functions — emits a structured invocation (function name and JSON arguments) instead of free-form text, letting downstream code execute the call deterministically.
• Tool Router
  A tool router is a layer in an agent system that selects which tool (or subset of tools) to expose to the model for a given query, instead of putting all tool definitions in every prompt.
• Tool Use (LLM)
  LLM tool use is the pattern in which a language model acts through external functions, APIs, databases or code execution: the model requests a tool, the host application runs it and returns the result, and the model continues, turning a text generator into a controller that can act. Function calling is the structured-output mechanism most tool use is built on.
• AI Agent / Agentic AI
  An AI agent is an LLM-driven system that, given a goal, plans a sequence of steps, calls tools or APIs, observes the results, and iterates until the goal is reached — going beyond single-turn chat to multi-step autonomous action.

More deployment & operations terms

• Browser-Use Agent
  A browser-use agent is an AI agent that operates a real web browser to complete tasks — clicking, typing, scrolling, and reading rendered DOM or screenshots — in place of using APIs.
• Code-Interpreter Agent
  A code-interpreter agent is an AI agent that writes and executes code (typically Python) in a sandbox to answer questions, run analyses, or transform data — using execution as a tool to escape the limitations of pure text reasoning.
• Model Latency
  Model latency is the time between request and response for a model inference call. For LLMs it decomposes into time-to-first-token (TTFT, dominated by the prefill stage) and time-per-output-token (TPOT, dominated by autoregressive decoding).