MCP Integration
A remote MCP server that puts your store's analytics and controls into Claude, Cursor, ChatGPT or any MCP client — around seventy tools, with the same approval gates.
If you would rather not open another dashboard, don't. DynoWeb runs a remote Model Context Protocol server, so your store's behavioural data and its controls become tools inside whatever AI client you already work in.
The practical difference: instead of navigating to a report, you ask in the place you are already thinking — and the answer arrives next to your code, your notes, or the rest of the conversation.
Connecting
Two paths, both landing on the same revocable token records.
OAuth — for clients that support it
Claude.ai's connector flow registers itself, you approve the connection in the DynoWeb admin, and the client receives a token. Standard OAuth 2.0 with discovery documents at the conventional well-known endpoints, so a compliant client configures itself from the endpoint URL alone. Redirect URIs are checked against an exact allow-list held in the codebase rather than accepted from the request.
Manual bearer token — for everything else
Issue a named token in the app and paste it into your client's custom-connector configuration. Same trust model as a GitHub personal access token: it is a secret, treat it like one.
Manage and revoke
Both kinds appear in one list with the client name, creation date and last-used timestamp. Revoking is immediate and uniform. Token issue and revoke events are audit-logged.
Works with Claude (desktop, web and Code), Cursor, ChatGPT's connector support, and any other MCP client.
What the tools cover
Roughly seventy tools, grouped by what they do. Every one is scoped to your shop.
Behavioural queries
Page views, funnels, scroll and form analytics, element metrics, event patterns, segment sessions, cohort comparisons, arbitrary breakdowns, storefront errors, and individual session deep-dives.
Analysis
Revenue analysis, trend-pattern detection, period comparison, metric calculation, store health score, customer-segment summaries, top sellers, churn-risk prediction, pricing optimisation and campaign planning.
Catalogue and content
List and inspect products, collections, pages, blogs and articles. Update products (including bulk and variant pricing), collections, pages and articles. Create pages and blog posts. Create discounts. Generate store imagery.
SmartNudge
The full lifecycle — list, inspect, create, update, delete, preview, publish, change status, plus cohorts, A/B tests, attribution, dashboard, trends, per-intervention stats and AI-generated suggestions.
Context and memory
Shop context, theme branding, navigation menus, plus save and recall of insights — so a conclusion you reached last week is available this week instead of being re-derived.
Capability discovery
A tool that lists what the server can do, so a client can orient itself without you maintaining a prompt full of tool names.
Safety carries over
An external client does not get a wider blast radius
Everything a tool can do through MCP, it does through the same code paths as the in-app agent. Writes are still gated. Actions are still logged with before-and-after snapshots and are still revertible. Usage is still metered against your plan, with writes costing more than reads.
The MCP surface changes where you drive from, not what is permitted. A remote client with a valid token is not more privileged than the app.
Tokens are shop-scoped: a token issued by your store can only ever read and write your store's data.
Worth doing when
- You are a developer. Reading conversion data next to the theme code you are about to change beats alt-tabbing to a dashboard and back.
- You want your own analysis. The query tools return structured data. Compose, join and chart it however you like, in a client that already does that well.
- You are building something. An internal report, a Slack digest, a weekly-summary agent — the tools are the API.
- You keep asking the same question. Save it as an insight, or wire it into a scheduled prompt in your client.
Limits
- A token is a credential. It grants a client full scoped access to your store's DynoWeb data and its write tools. Issue one per client, name them so you can tell them apart, and revoke on suspicion rather than on proof.
- Bounded by your plan, like everything else. MCP calls consume the same action allowance and AI budget as in-app use. A busy scripted loop will exhaust a daily allowance.
- Client quality varies. Tool discovery, argument handling and error surfacing differ substantially between MCP clients. A tool that behaves well in one client can be awkward in another.
- Data availability is unchanged. MCP is a different door onto the same data. If a page has no traffic, the tools will say so — they cannot query what was never tracked.
- Interactive OAuth needs a browser. A fully headless environment should use a manually issued token.
Related
DynoAgent
The same tool surface with DynoWeb's own model and UI in front of it.
AI Suggestions
Queryable over MCP, so the ranked queue can drive your own workflow.
SmartNudge
Fully drivable from an MCP client, creation through attribution.
Marketing overview: /features/mcp-integration.