VortexIQ MCP Connector
OfficialVortexIQ MCP Connector
Read-only Model Context Protocol connector for VortexIQ — an AI operating system for ecommerce.
Connect it to Claude (or any MCP client) and ask about your store's health, KPIs, alerts, brand voice, SEO drafts and more — in conversation, scoped to your own VortexIQ workspace. Every tool is read-only: the connector cannot create, edit, delete, publish or send anything.
Server URL:
https://app.vortexiq.ai/mcpTransport: Streamable HTTP (remote MCP server)
Auth: per-user OAuth 2.1 (Authorization Code + PKCE, S256)
Access: read-only, scoped to the signed-in user's organization
Connect
Claude (web / desktop)
Settings → Connectors → Add custom connector.
Server URL:
https://app.vortexiq.ai/mcpSign in with your existing VortexIQ (Google) login and click Allow.
The tools appear in Claude. Try "List my recent store audits."
You need a VortexIQ account. Data returned is scoped to your organization and your role's permissions.
Any OAuth client
The full OAuth 2.1 + PKCE flow (registration, authorize, token, refresh) is documented in MCP_OAUTH_LIVE_USAGE.md. Endpoints are machine-discoverable:
GET https://app.vortexiq.ai/.well-known/oauth-authorization-server
GET https://app.vortexiq.ai/.well-known/oauth-protected-resourceWhat you can ask
Prompt | Tools it uses |
"List my recent store audits, then show the findings for integration | store audit runs → report |
"What KPIs are available, and show the 30-day KPIs for | KPI library → integration KPIs |
"List my active Nerve Centre alerts and the 24h incident summary." | alerts → alert summary |
"Show my Brand DNA voice/tone guidelines." | brand profile |
"Show my Kanban health-fix backlog." | kanban board → fix items |
Tools (30, all read-only)
Full per-tool reference lives in docs/tools/ — one page per
tool with parameters, an example prompt, and what it returns.
Area | Tools |
Store Audit | list store audit runs · get store audit report · get store audit status |
Nerve Centre & KPIs | list nerve-centre alerts · get alert summary · list alert activity · get integration KPIs · list KPI library · get nerve integration counts · list nerve-centre profiles · list nerve configurations · list connector catalog · list monitors by type · get dashboard activity feed · list dashboard stores |
Brand DNA | get brand profile · list brand profiles · list brand ecommerce stores |
Ask VIQ | list Ask VIQ conversations · get Ask VIQ conversation |
Kanban (health-fix) | get kanban board · get kanban fix items · get kanban fix status |
Reports & Insights | list insights reports · list report profiles · list report schedules |
Inventory & Memory | list CloudHub inventory tabs · list Vortex memory files · list Vortex memory reports |
Deployments | get deployment history |
Notes & limitations
Read-only. No write, delete, publish or send tools exist.
Per-user scope. Each call runs as the connecting user against their own organization's data — there is no shared account.
Response caps. Some list results are capped (first 50 items / ~40k chars) to stay model-friendly; request a specific id to drill in.
Support
Email: support@vortexiq.ai
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/veevortexiq/claude-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server