Talk to your spaces from your favorite AI.
“In which day×hour windows am I losing sales to long queues across my Bogotá stores? Compare against last month.”
KSI MCP connects Claude, Gemini or ChatGPT to your stores' data: ask for reports, analyses and comparisons in natural language.
Compatible with Claude, Gemini, ChatGPT and other MCP-enabled LLMs.
MCP (Model Context Protocol) is the standard that lets AI assistants use external tools. KSI exposes your KPIs — traffic, conversion, queues, dwell time, zones — as tools your AI queries securely, with decision-ready analyses.
01 / HOW IT WORKS
Three steps and your AI is analyzing your stores
No development, no custom integrations: one URL and your KSI API token.
Generate your API token
From your profile in the KSI platform. The token is personal: it defines which stores and data your AI can see.
Connect the MCP URL
Add the connector in Claude, Gemini or ChatGPT with the KSI MCP URL and your token. One minute, one time.
Ask in your language
Request reports, analyses or comparisons. The AI queries real KSI data and answers with verifiable numbers.
02 / COMPATIBLE WITH YOUR AI
Works where you already work
KSI MCP implements the open Model Context Protocol standard, adopted by the leading AI assistants.
Anthropic · desktop, web and Claude Code
Google · Gemini CLI and compatible apps
OpenAI · apps/connectors and MCP-enabled API
Another tool? Any client that supports remote MCP (HTTP) can connect.
03 / WHAT YOU CAN ASK
Real questions, answers from real data
Every answer comes from your KPIs in KSI — not from the model's memory.
Weekly report in seconds
“Build this week's report: traffic, conversion and dwell time for every store, compared against last week.”
Store ranking
“Compare my 20 stores by conversion and traffic in June, grouped by region.”
Costly lost-sales windows
“On which days and hours is checkout saturation costing me sales? Give me the 5 most expensive windows.”
Staffing decisions
“Would opening more checkouts at peak hours improve conversion at equal traffic? Give me the verdict with evidence.”
Conversion by category
“How many unique visitors did each section get, and how does each category convert?”
Trust in the data
“How does KSI measure dwell time and how accurate is it? Explain it before I present to the board.”
04 / CAPABILITIES
20+ analysis tools
Your AI doesn't get raw data: it gets normalized KPIs and verdict-driven analyses, with the same validated logic as the KSI platform.
Diagnostics
What data each store has, before asking for it.
- ·Per-store capabilities
- ·Physical structure
- ·Methodology of every indicator
Normalized KPIs
Clean series, in each store's timezone.
- ·Traffic and floors
- ·Queues and SLA
- ·Dwell time and zones
- ·Sales and conversion
- ·Demographics and vehicles
Verdict-driven analyses
Actionable conclusions, not tables to interpret.
- ·Queue saturation vs sales
- ·Impact of opening more checkouts
- ·Conversion goals
Comparisons
Multiple stores or periods in a single question.
- ·Store benchmarks
- ·Periods (vs previous or last year)
- ·Stores within a mall
05 / SECURITY
Your data, under your control
Personal token
Each user connects with their own KSI API token: the AI only sees what that user can see.
Nothing is stored
The token travels with each request and is never persisted on the MCP server. No copies of your data.
Read-only
The MCP queries indicators. It never modifies configuration, cameras or data.