Human-in-the-Loop Agent Task Management for Claude Code
Back to Glossary

MCP (Model Context Protocol)

MCP (Model Context Protocol) is an open protocol developed by Anthropic that standardizes how AI agents connect to external tools, data sources, and services. MCP defines a common language that MCP clients (like Claude Code) use to communicate with MCP servers (like AgentRQ) — enabling a rich ecosystem of interoperable agent capabilities.

Why MCP Exists

Before MCP, every AI tool had to build custom integrations for every service it wanted to connect to. This created a fragmented ecosystem where each LLM provider and each tool had incompatible APIs.

MCP solves this with a standard protocol. A server built to the MCP spec works with any MCP-compatible client, and a client built to the MCP spec can use any MCP server — without custom code.

MCP Architecture

`

AI Agent (MCP Client)

│ MCP Protocol (JSON-RPC over stdio/SSE/HTTP)

MCP Server (e.g., AgentRQ)

External Service / Tool

`

The protocol has three primitives:

MCP and AgentRQ

AgentRQ is an MCP server. When you add AgentRQ to your Claude Code configuration, Claude Code becomes an MCP client that can call AgentRQ's tools:

MCP Transport Options

Transport Description
stdio Local server, communicates over stdin/stdout
HTTP + SSE Remote server, uses HTTP for requests and SSE for streaming

AgentRQ uses HTTP + SSE transport, enabling real-time notifications from anywhere.

Related Terms

Start Free