JSON-RPC 2.0
Industry Definition Set • Entity Resolution Path: /glossary/json-rpc
Quick Answer / TL;DR
A lightweight, stateless remote procedure call (RPC) protocol defined in JSON that utilizes request, response, and notification message frames.
Key Takeaways
- Stateless protocol designed for low communication overhead.
- Distinct formats for request-response loops and one-way notification events.
- Perfect error representation structure with standardized numeric codes.
- Language-neutral format implemented across all programming stacks.
Technical Context & Protocol Usage
JSON-RPC 2.0 is the transport-agnostic message format chosen for the Model Context Protocol. It defines exact JSON schemas for client requests (containing 'jsonrpc', 'method', 'params', and 'id'), server responses (containing 'jsonrpc', 'result', or 'error', and 'id'), and notification frames (without an 'id' for fire-and-forget events). Because it is simple and highly structured, it can be parsed instantly by models and systems alike.
Format & Payload Metadata
Format: IETF RFC 4627 compliant JSON payload
Latency: Negligible parse/serialize duration (<0.5ms)
Real-World Implementation Use Case
Encoding a tool execution command like 'callTool' with parameters, and parsing the exact output returned by the backend server.
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.
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.
MCP Server
An application that implements the Model Context Protocol, hosting tools, resources, and prompt templates, responding to JSON-RPC requests from compliant AI clients.
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