What is VCP?

A protocol for portable, adaptive, live context across AI and services.

VCP is not a product. It is an open protocol that lets you define your preferences, constraints, and current state once — and have every compatible AI and service adapt to you automatically, in real time.

Three Properties That Matter

Today your context is fragmented across services, static, and invisible. VCP makes it portable, adaptive, and live.

Portability

Define your context once. Every AI and service you use receives it automatically — no re-entry, no repetition.

Adaptation

Context switches with your situation. Work mode at the office, personal mode at home — the right profile activates automatically.

Liveness

Your real-time state shapes AI guidance moment to moment. Rushed? Stressed? The AI adjusts its tone and depth instantly.

How It Works

You declare your context. VCP encodes it as structured data. Services read the flags and adapt — without seeing the private reasons behind them.

You Set Context

Define your goals, constraints, and current state. Mark what is shareable and what stays private.

VCP Encodes It

Private circumstances become categorical flags. "Thin walls" becomes noise_restricted. The flag travels. Your story stays home.

Services Adapt

Every compatible app and AI reads the flags and adjusts. When your state changes, every service updates in real time.

The Protocol Stack

VCP is a six-layer protocol stack (I-T-S-A-M-E) — like the OSI model but for AI values.

VCP/I — Identity

Token naming, namespaces, and registry. What is it called?

VCP/T — Transport

Signed bundles, verify-then-inject. How is it delivered safely?

VCP/S — Semantics

CSM-1 grammar, personas, composition. What does it mean?

VCP/A — Adaptation

Context encoding, state tracking. When and how does it apply?

The Three-Layer Model

Within the Adaptation layer, VCP organizes context at three timescales — stable rules, shifting situations, and moment-to-moment state.

Constitutional Rules

What the AI should and should not do.

Personas, safety boundaries, rulesets, adherence levels

Changes rarely

Situational Context

Where, when, who, what occasion.

Morning vs. evening, alone vs. with children, home vs. work

Changes per session

Personal State

How you are right now.

Cognitive load, emotional tone, energy, urgency, body state

Changes moment to moment

Not a Magic Mirror

You declare your context. The AI adapts to what you share, not to what it guesses.

Common Approaches

VCP Approach

AI infers your state

You declare your state

Context locked to one platform

Context travels across platforms

Static profile, set and forget

Live state, always current

Platform decides what to share

You control what is shared

Works With MCP

VCP integrates natively with the Model Context Protocol (MCP). MCP is the delivery channel. VCP is the structured content it carries.

MCP

Transport

Connects AI agents to tools and data sources. The plumbing.

VCP

Policy

Encodes values, context, and constitutional rules. The meaning.

Any MCP-compatible agent can call VCP tools to discover what constitutional rules apply, encode the current context, and adapt behaviour accordingly. VCP also integrates via REST API, export artifacts, and GPT Actions.