---
id: "entity-mcp-d21"
type: "entity"
entityType: "tool"
canonicalName: "Model Context Protocol"
aliases: ["MCP"]
source_timestamps: ["00:00:28", "00:01:47", "00:03:48"]
tags: ["protocol", "integration"]
related: ["concept-agent-door", "concept-open-brain", "concept-shared-surface"]
sources: ["s21-ai-tool-memory"]
sourceVaultSlug: "s21-ai-tool-memory"
originDay: 21
---
# Model Context Protocol (MCP)

## What It Is
The **Model Context Protocol (MCP)** is an open standard that allows AI models to securely connect to local or remote data sources.

## Role in This Source
In the [[concept-open-brain-d21]] architecture, an MCP server acts as the [[concept-agent-door]] — the programmatic pathway through which the AI agent reads from and writes to the [[entity-supabase-d21]] database.

## Why It Matters
- **Model-agnostic**: any frontier model with MCP support (e.g., [[entity-claude-d21]]) can speak to the database.
- **Future-proof**: this is the protocol substrate that powers [[concept-ai-flywheel]] — when models improve, the same MCP setup automatically benefits.
- **No middleware**: paired with the [[concept-shared-surface]] principle, MCP eliminates the need for export layers or sync middleware — see [[claim-no-sync-layer]].

## Setup
The MCP server is configured during [[prereq-supabase-mcp-setup]]. Once set up, every new table added via [[framework-open-brain-build]] is automatically reachable through the same MCP server.