MCP Resources / Resource
Industry Definition Set • Entity Resolution Path: /glossary/resource
Quick Answer / TL;DR
Static or dynamic data inputs (such as files, databases, or API readouts) that servers expose to the client as read-only context feeds for the model.
Key Takeaways
- Read-only contextual data feeds for AI models.
- Organized using a custom URI-scheme structure (e.g. 'postgres://').
- Supports push-notification updates when resource data changes.
- Optimizes token count by letting models query only what is needed.
Technical Context & Protocol Usage
Resources are the passive, informational assets of MCP. They represent anything that can be read, such as text documents, server configs, application logs, or database rows. Resources can be static files referenced by URI (like 'file:///workspace/package.json') or dynamic resource templates (like 'database://{table}/schema') that clients query on-demand.
Format & Payload Metadata
Format: Base64 encoded binary or standard UTF-8 text strings
Latency: Extremely lightweight data transfer speeds
Real-World Implementation Use Case
Allowing an AI model to read real-time application error logs directly from a 'logs://today' URI context stream.
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