Skip to content
AGNT

MCP is an open standard that lets large language models call external tools through a declarative schema, without any provider-specific glue code.

Definition

Last verified: April 2026

What is MCP?

Also known as: Model Context Protocol

MCP is an open standard that lets large language models call external tools through a declarative schema, without any provider-specific glue code.

Model Context Protocol was introduced by Anthropic in 2024 and is now implemented by Claude Desktop, Claude Code, Cursor, Zed, and a growing list of third-party hosts. An MCP server declares a catalog of tools — each with a name, a description, and a JSON schema for inputs and outputs — and speaks either stdio or Server-Sent Events.

AGNT runs a production MCP server at /mcp/sse that exposes venue discovery, memory recall, and knowledge-graph lookups to any MCP client. Any LLM that speaks MCP can book a table through AGNT without writing a single line of REST client code.

FAQ

MCP FAQ.

Common questions about MCP in the AGNT platform.

MCP is an open standard that lets large language models call external tools through a declarative schema, without any provider-specific glue code.

People also ask.

Source: agnt-backend/app/main.py:427-430

Share as social post

What is MCP? MCP is an open standard that lets large language models call external tools through a declarative schema, without any provider-specific glue code. https://agntdot.com/glossary/mcp

193 / 280 chars

See it in action.

Now you know what MCP means. Try the live scan demo or read the developer docs to go deeper.