Bring your own agent

This is a live preview of the whole architecture, built for Claude Code (other MCP-capable agent harnesses can often figure out the flow too). You bring the agent and drive the full lifecycle yourself — author a policy, propose a product, and read back a cryptographically verified verdict — against the real Shopify catalog over UCP.

This is a preview, not the MCP integration surface

Don’t confuse this with the MCP page — that’s the managed, policy-authoring surface (author only). Here, we run the orchestrator and the rest of the infrastructure, with an MCP on top that your agent connects to directly to drive the whole flow: author, sign the intent, propose, and read the outcome. It’s the bring-your-own-agent counterpart to the hosted Son of Anton preview, where delta runs the agent and the UI for you.

Prerequisites

• The Claude Code CLI.
• Shopify UCP (the ucp skill + CLI), for product discovery — set up below.

1. Install

curl -fsSL -X POST https://delta-mandate-mcp.repyhlabs.dev/install | sh

Mints your identity and wires the MCP into Claude Code. Re-running /install creates a fresh identity.

Then run claude and type /mcp — you should see delta-mandate connected with 5 tools.

2. Set up Shopify UCP tools

You need the ucp CLI for product discovery. If it isn’t installed yet, Claude Code can set it up autonomously when needed.

The agent uses it to find products in Shopify’s Global catalog via UCP and propose a variant — delta mandate extracts the evidence straight from that exact variant.

The ucp skill mentioned in the link above isn’t strictly necessary, but it improves the agent’s efficiency at catalog search.

3. Use it

In Claude Code, type:

use delta-mandate to find me a black leather wallet under $50

What happens behind the scenes?

The agent drives it by calling the delta-mandate MCP’s tools (step 3 is the separate Shopify ucp CLI):

1. get_language_guide + search_taxonomy — learn the DSL, find the product’s taxonomy category.
2. submit_policy — author and validate the policy → policy_id.
3. Search Shopify UCP (the ucp CLI) for a matching variant → its ProductVariant GID.
4. submit_proposal (policy_id + GID) — signs and submits the intent → intent_id.
5. get_outcome (intent_id) — read the verified verdict.

Want to see a rejection?

Give an over-strict constraint (e.g. a price far too low). The agent proposes the closest match and the evidence layer fails it — a failing verdict is a valid result: it means delta mandate caught a real mismatch between your policy and the product’s extracted evidence. You can also tell your agent to propose a different product or variant to see a rejection; the possibilities are endless!

What it can (and can't) enforce

A policy can only constrain attributes the taxonomy exposes for a category, so some asks have no field — e.g. brand (“Nike”) isn’t a taxonomy attribute and can’t be enforced (the agent will tell you what it can enforce and what it has to drop). This preview works only against the Shopify catalog over UCP, using the Shopify Standard Product Taxonomy.