Vortex IQ MCP connector: query your workspace from Claude

Connect Claude (or any MCP client) to Vortex IQ and ask about store audits, KPIs, Nerve Centre alerts, Brand DNA, Kanban fixes and more — 30 read-only tools, scoped to your own workspace.

The Vortex IQ MCP connector gives Claude — and any other Model Context Protocol client — read-only access to your Vortex IQ workspace. Once connected, you can ask about your store’s health scores, KPI trends, active alerts, brand voice guidelines, health-fix backlog and more, in plain English, without opening the dashboard.

Every tool is read-only: the connector cannot create, edit, delete, publish or send anything. Each call runs as the signed-in user, so the data returned is always scoped to your own organisation and your role’s permissions.

At a glance

Server URL	https://app.vortexiq.ai/mcp
Transport	Streamable HTTP (remote MCP server)
Authentication	Per-user OAuth 2.1 (Authorization Code + PKCE, S256)
Access	Read-only, scoped to the signed-in user’s organisation
Tools	30, across Store Audit, Nerve Centre, Brand DNA, Ask Viq, Kanban, Reports, Inventory and Deployments
Requirements	A Vortex IQ account

Connect to Claude

Add the connector in Claude web, desktop or Claude Code in under two minutes.

Tool reference

All 30 read-only tools with parameters and example prompts, grouped by area.

OAuth for developers

The full OAuth 2.1 + PKCE flow for connecting any custom MCP client or agent.

What you can ask

Once connected, Claude picks the right tools automatically. Some starting points:

Prompt	What happens
”List my recent store audits, then show the findings for integration <id>.”	Lists audit runs, then pulls the full findings report with health score.
”What KPIs are available, and show the 30-day KPIs for <integration>.”	Browses the KPI library, then fetches KPI cards and trends for that integration.
”List my active Nerve Centre alerts and give me the 24h incident summary.”	Returns active alerts plus the last-24-hours incident counts.
”Show my Brand DNA voice and tone guidelines.”	Fetches your Brand DNA profile for use while drafting content.
”Show my Kanban health-fix backlog.”	Returns the board state, and can drill into a fix run’s before/after changes.
”List my connected integrations and their status.”	Summarises the organisation’s connector graph and connection counts.

How it works

The connector is a native MCP server co-located with the Vortex IQ OAuth authorization server at app.vortexiq.ai — there is no separate proxy. When you add it, Claude walks you through a standard OAuth sign-in with your existing Vortex IQ (Google) login. Your access token is forwarded on every tool call, so every result reflects exactly what your account can already see in the dashboard.

All 30 tools carry the MCP readOnlyHint. The connector has no write, delete, publish or send capability of any kind — it cannot modify your workspace, your stores or your data.

Known limitations

• Read-only. The connector cannot create, edit, delete, publish or send anything.
• Per-user scope. Each call runs as the connecting user against their own organisation’s data — there is no shared or service account.
• Response caps. Some list results are capped (first 50 items / roughly 40k characters) to stay model-friendly. Ask for a specific id to drill into full detail.

Support

• Documentation: docs.vortexiq.ai
• Privacy policy: vortexiq.ai/privacy-policy
• Email: [e-mail]