NOW LIVE CORE DNA MCP

Let Claude and ChatGPT update your content, products and pages

Book a demo
Let Claude and ChatGPT update your content, products and pages
60+
tools · AI agents · 400+ APIs
Content, products and pages across your Core dna sites

Inside your permissions and approvals.
Every change is logged and can be undone.

Watch Core dna MCP in action

What Claude and ChatGPT can change in Core dna

Core dna is a website and ecommerce platform for organizations running many websites and stores. Through its MCP server, 60+ tools across 22 modules cover the content, products and pages in your sites.

  • Content and pages. Write, duplicate and publish pages from your templates, with full revision history.
  • Products and prices. Change tiers, RRP and promotional prices across hundreds of SKUs, through your approval steps.
  • Search across properties. Find pages by slug, copy, SEO, category, tag or region.
  • Blogs, FAQs, forms and custom entities. Every content type your sites use.
  • Files and images. Upload, replace or reuse files from your library.
  • Your custom fields. The agent reads your schema as it works, so new fields are ready straight away.
Tool spotlight illustration
What runs underneath every prompt FOUR GUARDRAILS · BUILT IN

Permissions and approvals for AI agents

The MCP server stays off until your Core dna account manager switches it on. From then on, it inherits the security model, approval workflows, revision history and audit trail you already run.

01 YOUR SECURITY · IN AGENT FORM

Your security model, applied to every prompt

The agent inherits the role and permissions of whoever signed in. A junior with read-only stays read-only. A regional marketing lead can change their region and nothing else. You can also limit agents to read-only or block deletes, without changing anyone's role.

See roles and permissions
02 REVIEW · APPROVAL · ROUTING

Workflows route the work the way you already work

The agent doesn't bypass your approval steps. Content, product and price changes are drafted, sent for approval and published only after sign-off. Two-person rules, regional approvers, content review queues - whatever your team already runs in the admin, the agent runs in plain English.

See approval and governance
03 EVERY PROMPT · A REVISION

Every prompt is a revision. Every revision rolls back.

Every change the agent makes is a versioned revision in Core dna. Diff the edit. Roll back the prompt. Compare a draft to the active version. The platform you already trust catches every change before it ships.

See how version control works
04 EVERY PROMPT · LOGGED

Audit trail per prompt, per session, per change

Who prompted what. What the agent did. What was approved. What was rolled back. A complete audit log per agent, per session, per content change. The kind of trail procurement, security, and compliance teams sign off on without a second meeting.

See how to govern AI agents
1,700 PAGES TRANSLATED THROUGH MCP SAVE A LIFE

We were running four separate systems, WordPress, Shopify, a custom LMS, and a DevOps pipeline to hold it together. Core dna replaced all of it.

Mackenzie Thompson
CEO, Save a Life
Read the localization story
~1,700
pages translated by AI through MCP
~1M
words of clinical content
100%
approved by a medical advisor
4 → 1
systems replaced by Core dna
Features illustration

New in MCP 2.0: build your own features

Every business has rules its website should follow. Who gets which enquiry. When a customer is asked for a review. When a sale starts, and when the prices go back.

With MCP 2.0 you describe those rules in plain language, and your AI assistant builds them into your Core dna site as working features: the content they need, the logic, and the automations that run them. Work that used to need a development project now starts with a brief.

  • A review system. A review request a week after each order, an approval step for every review, and star ratings from the approved ones.
  • Lead routing. Each enquiry sent to the sales team for the person's region, with a confirmation email.
  • A timed sale. A landing page and price changes that start on Black Friday and end after Cyber Monday.
  • Live form reporting. A private report page for every web form. Our CTO had Claude build it from one brief, for forms with more than 300,000 entries.
  • Your approval first. New automations stay off until you switch them on, and new content starts as a draft.
Try MCP 2.0

See how our CTO built a feature from one brief →

MCP

Connect your AI agent to Core dna

Three steps, plain language, your approval where you want it.

Connect
Ask
It acts

Multi-property jobs teams send the agent every week

These are the kinds of rollouts marketing, ecommerce, and ops teams send their agent every week - from a single chat window, to every property you run.

Red floral abstract pattern with intricate petal designs

Launch a campaign across every property

“Marketing just signed off this Word doc. Turn it into a landing page under each location’s /promotions/ folder - hero, three feature columns, a testimonial, our standard footer CTA.”

Paste the doc once. The agent picks layouts that match your existing location pages, builds the structure, fills in SEO, and creates a draft per property for review.

Abstract red shape with intricate design on a white background.

Update one property, leave the other 199 alone

“On the Austin store page, change the promo heading to ‘Now Open Sundays’, update the hours block, and point the CTA at /austin/book.”

A surgical, single-property edit. The agent finds the right page and the right blocks and changes only those fields. Nothing else moves.

Abstract red swirl design with geometric shapes and paths.

Roll a banner out to every property at once

“Add a ‘Holiday hours – check your local store’ banner above the footer on every location in the Southeast region. Button text ‘Find my store’, link to /locations.”

A bulk rollout from one prompt. The agent lists the region, drafts the banner once, and applies it across, with optional per-property approval if you want eyes on each one.

Abstract geometric design with red shapes on a white background.

Localise pages for a regional market

“Translate the Miami location page into Spanish and create it under our /es/ root. Keep every image and link the same, just swap the copy.”

The agent duplicates the page, walks every nested text area, translates in place, and saves it as a sibling under the Spanish root. One conversation, no agency handoff.

Red gear icon on a pink background with decorative elements.

Reprice hundreds of SKUs in one prompt

“For every product in the Outdoor category, increase RRP by 8%, round to the nearest dollar, and flag any item where the new RRP is more than 20% above the current promotional price.”

Bulk pricing edit plus a sanity-check report. The kind of operation that lives in a spreadsheet today, run in plain English in a single agent session.

Abstract geometric shapes in shades of pink and red with a complex pattern

Find every stale detail across every property

“Find every page still listing the old support number 1-800-555-0100 and update it. While you’re at it, flag any page linking to /old-offers.”

A cross-property audit, bulk fix, and housekeeping report. The nine-months-overdue cleanup nobody had time for, done in one prompt.

Abstract geometric background with light colors and a grid pattern.

Your portfolio, now agent-native

MCP stands for Model Context Protocol, the open standard that lets any AI agent act inside a platform like Core dna. Every modern agent already speaks it. What matters isn't the connection, it's what sits on the other end of it: not a single site, but every property Core dna runs for you. The same prompt that changes one page changes two hundred.

So the agent in your browser does the rollout instead of talking about it. Launch a campaign page across every region. Swap a seasonal banner on 200 properties at once. Update store hours brand-wide. Plain English, from the chat window you already have open.

  • Per-property control when you need it, brand-wide reach when you don't.
  • One prompt, scoped to one store or every store in a region.
  • Brief the change once. The agent applies it across every property, not one page two hundred times by hand.
  • One agent reaches your website and store, your inbox, your calendar and your CRM.
  • Core dna is one stop on the agent's map, not a walled garden.
  • No new logins. Your Core dna identity is the identity, and the agent can only do what that account can do.

How to switch it on for your sites

Step 1 - Enable CIMD and DCR on your tenant
Step 2 - Connect your AI agent
Step 3 - Connect ChatGPT, Gemini, Cursor, Copilot
Step 4 - Brief your first rollout

Works with every major AI agent

Nine clients tested in production. One protocol underneath. Pick the one your team already lives in.

Claude.ai

DCR or CIMD
Works today, the primary supported path.

Build a website with Claude →

Claude Desktop

DCR or CIMD
Works today via mcp-remote or native.

Build a website with Claude →

Claude Code (CLI)

DCR + loopback
Works today, ephemeral-port flow.

Build a website with Claude →

ChatGPT (Apps)

DCR
DCR works today.

Build a website with ChatGPT →

OpenAI Codex CLI

DCR + loopback
Works today via codex mcp login.

Google Gemini CLI

DCR (dynamic discovery)
Works today out of the box.

Cursor IDE

DCR (per-connect)
Works today. Cursor re-registers per session, handled automatically.

Microsoft Copilot

Pre-registered client
Works today via Copilot Studio.

Aider · Continue · Cline

DCR + loopback
Works today. The same flow every OSS coding agent uses.

OAUTH 2.1 · NO SECRETS · PER-REQUEST AUDITABLE

Security your IT team will sign off on

No client secrets ever touch the AI agent. The agent’s browser proves possession of the auth code with a cryptographic verifier. This is what Claude and most modern AI clients use by default - the OAuth 2.1 standard for public clients, and the safest option for software running on someone else’s machine.

No admin pre-registration, no tickets. On first connect, the AI agent calls the /oauth/register endpoint, gets a fresh client_id, and is good to go. Stale registrations are cleared after seven days. Used by ChatGPT, Claude Code, Codex, Gemini, Cursor, and every open-source IDE.

The AI agent’s client_id is itself a URL pointing to its own metadata document. Core dna fetches it, validates it, and pins the hash. The agent is identified without ever pre-registering. Used by Claude.ai today as the primary path.

REAL PROMPTS · REAL ACTIONS · ONE CONVERSATION EACH

What it looks like when you brief the agent.

Three prompts a multi-property team sent the agent this quarter. Same chat window, every property, one conversation each.

“Increase RRP by 8% for every product in the Outdoor category. Round to the nearest dollar. Flag anything over 20% above promo.”
“Translate every location page into Spanish under /es/.”
“Add a holiday-hours banner above the footer on every Southeast location.”

Your agent files its own bug reports. You just say the word.

When your agent hits a rough edge - an undocumented field, a confusing error, a tool that misbehaves - the conversation doesn’t have to end there. The Core dna MCP includes a feedback tool that ships the agent’s experience straight to the engineering team.

You don’t have to describe what went wrong. The agent already knows. It hit the friction. You just have to ask.

  • One line to invoke. Say ‘submit feedback to MCP’ and the agent writes the report - tool calls, payloads, and error messages included.
  • Zero overhead for you. No bug tracker login, no reproducing the issue, no screenshots.
  • Your edge case becomes the roadmap. The next team to try the same thing never hits the wall.
Interface showing translation review workflow with language options and approval process.

Agents that run on platform events and schedules

Beyond the chat window, agents run inside the Core dna orchestration engine. They start on a platform event or a schedule and work under the same permissions, approvals, audit trail and rollback as every prompt.

See agentic workflows →

Live
Triggered by what happens on your sites

A new product, a stock level below threshold, or an order that needs review can start a scoped agent run. You set which events trigger which agents, and which changes need sign-off.

Live
Scheduled sweeps across every property

Agents run nightly checks across every property, covering SEO fields, broken links, missing alt text and expired promotions. They fix what's in scope and queue the rest for approval.

FAQ

Questions about connecting Claude and ChatGPT to Core dna

Core dna. Core dna is a website and ecommerce platform for organizations running many websites and stores. Its MCP server lets Claude, ChatGPT and other AI agents update content, products and pages within your existing role permissions and approval workflows. Every change is saved as a revision you can review, approve and roll back.

Yes. Through the Core dna MCP server, Claude, ChatGPT and other AI agents can edit products, pricing tiers, RRP and promotional prices, including bulk changes across hundreds of SKUs. Price changes follow the same approval workflow as content.

No. The agent works inside your existing approval workflow. Its changes are saved as unpublished revisions and go live only after the sign-off your workflow requires.

You do. The agent inherits the role and permissions of the person who connected it, so it can only do what that person can do. You can also limit AI agents to read-only or block deletes, separately from what people can do in the admin.

No. It stays off until your Core dna account manager enables it for your sites. Each person then connects their AI agent with their own Core dna login, and you can revoke that access from the admin at any time.

Yes. Every change is a versioned revision you can compare with the live version and roll back. The audit log records who prompted what, what the agent did, what was approved and what was rolled back.

Claude (claude.ai, Claude Desktop and Claude Code), ChatGPT, OpenAI Codex CLI, Google Gemini CLI, Cursor, Microsoft Copilot through Copilot Studio, and open-source agents such as Aider, Continue and Cline. They connect through MCP, the open standard for AI agents.

No. You sign in with your existing Core dna login and approve the connection. Access uses OAuth 2.1, so no client secrets or API keys are shared with the agent, and tokens are scoped to your account and can be revoked.

FROM THE BLOG

Latest on AI & emerging tech

GET STARTED

See how a multi-property team runs every site, store, brand, and location through a single agent, with the security, workflows, version control, and audit trail you already trust.