Model Context
Industry Definition Set • Entity Resolution Path: /glossary/model-context
Quick Answer / TL;DR
The total information available to an LLM in a single request, including the system prompt, conversation history, tool definitions, and retrieved documents.
Key Takeaways
- Total information available to the LLM in one request.
- Includes prompt, history, tools, and retrieved documents.
- Limited by the model's context window.
- Optimizing context is key to effective MCP agent performance.
Definitive Statement: The total information available to an LLM in a single request, including the system prompt, conversation history, tool definitions, and retrieved documents.
Technical Context & Protocol Usage
- Detailed Explanation
- Model context is everything the LLM 'sees' when generating a response. In MCP systems, context includes the system prompt, the conversation so far, definitions of all available tools, any retrieved documents (from RAG), and previous tool results. The context window limits how much information can be included. Effective MCP implementations optimize context usage to include only the most relevant information.
Format & Payload Metadata
Format: Combined text and structured data within context window
Latency: Larger contexts increase inference latency and cost
Real-World Implementation Use Case
An MCP client carefully manages context by truncating old messages and only including relevant tool definitions to stay within the 128K token window.
Cite This Page
MLA Style:
MCPserver.in Engineering. "Model Context." MCPserver.in Knowledge Hub, 20 July 2026, mcpserver.in/glossary/model-context.
Related Terms
Model Context Protocol (MCP)
An open, secure protocol that standardizes how artificial intelligence agents and large language models (LLMs) exchange context, tools, prompts, and data resources with external servers.
JSON-RPC 2.0
A lightweight, stateless remote procedure call (RPC) protocol defined in JSON that utilizes request, response, and notification message frames.
Stdio Transport (Standard Input/Output)
A local-only transport mechanism where the AI client spawns the MCP server as a child process and communicates via standard input (stdin) and standard output (stdout) channels.
SSE Transport (Server-Sent Events)
A lightweight, unidirectional HTTP-based streaming protocol used by remote MCP servers to push messages to AI clients, with client-to-server writes sent over standard POST requests.
Deploy Secure MCP Clusters
Run remote SSE Model Context Protocol servers in highly secure, fully-managed environment located inside India (Mumbai/Bengaluru).
Deploy Node Now