---
id: "concept-model-context-protocol"
type: "concept"
source_timestamps: ["00:01:18", "00:12:30", "00:20:18"]
tags: ["protocols", "interoperability"]
related: ["concept-open-brain", "concept-agent-web"]
definition: "An open standard protocol (described as the USB-C of AI) that allows any AI model to securely connect to and query external, user-owned data sources."
sources: ["s22-saas-replacement"]
sourceVaultSlug: "s22-saas-replacement"
originDay: 22
---
# Model Context Protocol (MCP)

## Definition

An open standard protocol — described by the speaker as **'the USB-C of the AI age'** — that allows any AI model to securely connect to and query external, user-owned data sources.

## Origin

Launched as an open-source experiment by [[entity-anthropic-d22]] in late 2024, MCP rapidly became the de-facto standard transport for AI agents to read and write external context. (Note: the enrichment overlay flagged that independent corroboration of the late-2024 Anthropic launch claim was thin in third-party sources — treat the date claim as speaker-attributed; see [[question-corporate-response-mcp]].)

## Role in the Open Brain

MCP is the bridge between the user's [[entity-postgresql]] / [[entity-pgvector]] database and any AI front-end:

- A single MCP server fronts the personal database.
- Claude Desktop, Cursor, custom scripts, future models — each speak the same MCP wire format.
- When a new SOTA model ships, you do not migrate data. You just point the new client at the existing MCP server.

This is what makes the [[concept-open-brain-d22]] truly **portable** and breaks the dependency on proprietary SaaS integrations described in [[concept-memory-silo-problem]].

## Implementation Hook

The operational step is captured in [[action-connect-mcp]]: stand up an MCP server that exposes your Postgres+pgvector database to your preferred AI clients.