The data exists.
The work is making it readable.
One archive, normalised, yours.
Customer records in the management system, hours in HR, orders in the e-commerce, the rest in spreadsheets. Every system keeps its data in the format that suits itself: reading them together takes a technical job every single time. Normalising means stopping doing that job again.
Four dependencies fewer. And no new ones.
- 01
From your ERP's roadmap
You don't have to wait for the vendor to build the feature you need. The layer evolves at your pace, not theirs.
- 02
From the ERP vendor
If you switch management systems one day, the history stays where it is: one input source changes, you don't start over.
- 03
From the model you'll use
No LLM is wired in. One today, another tomorrow, or one on-premise: the consumer changes, the infrastructure doesn't.
- 04
From the single tool
With an MCP server the data is available to any tool that asks for it, securely and traceably.
The code is yours. And so is the data. Whatever you decide next.
One archive, readable without instructions.
A management system writes data for itself: a single product ends up across several tables, with field names designed for the machine that fills them in. That isn't a flaw: it's built to record, not to be questioned. Normalising means putting it back into a readable structure - explicit names, a single unit of measure, the relations in the right place - for whoever needs to find it: a person or an agent.
CLI_ANA.RGSOC1ACME SRL
CLI_ANA.PIVA0841…968
ORD_TES.DTORD20250914
ART_MAG.QTA_DISP12,000
ts.hours7.5
ts.project_refACM-25
dept.codeOPS
customer.emailordini@acme…
order.created_at2025-09-14
order.total1240.00
The data layer
A relational database that imports from ERP, HR, e‑commerce and spreadsheets. Every source keeps its origin, but speaks a single language.
The middleware
The engine that keeps the data current and exposes it through controlled APIs. No system touches the management software directly any more.
The MCP server
The layer that makes the data readable by an LLM: any model, any tool, always within the permissions of whoever is asking.
Worth it even if AI never arrives.
Cross-referenced data without asking anyone
ERP and HR in the same question: people, costs and activity in one go.
Numbers without going through IT
Whoever needs a figure takes it, without opening a ticket.
Integrations that stop multiplying
Systems draw from a single, current source. Fewer exports, less copy-pasting.
Four phases. A deliverable at every step.
- $ 01 · map
Mapping - where the data is and what it costs to bring it together.
- $ 02 · model
Data model - entities, relations, granularity.
- $ 03 · pipe
Ingestion and APIs - with permissions in the right place from day one.
- $ 04 · mcp
AI access - data queryable in natural language and available to agents.
The phases are bought one at a time. You don't need to sign for all of it to start: the mapping is already a finished piece of work, even if the project goes no further. And with a single application and few users, a good export and a well-written query solve the same problem with fewer resources: these are things you see during mapping.
Company DWH with middleware and MCPSee how we did it