MCP & AI
From question to dashboard
Pyro answers data questions, shows charts in chat and builds dashboards. Your own agents connect through MCP.
- Choose your own model
- Changes require your approval
Cloud convenience. Your infrastructure.Data cloud for AI & analytics.
Data cloud for AI & analytics.
In your own data center.
A data warehouse and lakehouse for AI, SQL and dashboards in one platform. You choose the location and compute capacity: your data center, rented servers or the cloud. Predictable platform licensing, no credits per data query.
- AI
- Ask questions, find knowledge, create dashboards
- MCP
- Connect your own agents to your data
- 1
- Console for data, AI and governance
- 100%
- Your infrastructure for the data platform
Meet Pyro
One question. Your data comes to life.
Pyro helps you understand data, create dashboards and prepare workflows. Right inside lavalake, with your permissions.
More about PyroPyroPyro · Your AI assistant
With your permissions
Hi, I’m Pyro.
I help with your data and platform — with your permissions, and changes only after your approval.
Illustrative sample data · not a live chat
AI in practice
What your assistant can do with lavalake
Ask questions. Put your data to work.
The assistant can explore data, query defined metrics and create dashboards. You work in natural language; tools execute each step under your identity. This example illustrates a possible workflow using a previously defined revenue metric.
Read the docs- 1
Ask a question
How is our revenue developing by region?
The assistant queries a previously defined metric.
- 2
Approve a dashboard
Create a dashboard from this.
Review the proposed change and confirm it.
- 3
Analyze together
One view for your team
Each tile runs under the permissions of the person viewing it.
The AI data platform
Built for agents, not retrofitted.
Connect data, find answers and control access in one platform.
Governance
Your permissions apply to your AI too
People and agents work under the same permissions. Access and changes remain traceable.
- Row filters and column masking
- Logged actions and data lineage
Getting data in
Make business data available to AI
Upload Excel, CSV and documents. lavaflow connects sources, transformations and targets in visual workflows.
- Import databases, Excel, CSV and documents
- File ingestion, delta loads and PostgreSQL CDC
Knowledge & metrics
One knowledge base for people and agents
Use the same defined metrics across search, SQL, dashboards and AI answers.
- Local semantic search
- AI functions directly in SQL
Architecture
Cloud convenience for data and AI. On your infrastructure.
One web console for data imports, SQL, search, AI assistance and dashboards. Underneath sits an open Iceberg lakehouse with separate storage and compute. Run lavalake in your data center, on rented servers or in a private cloud. You do not need your own data center or admin team: an IT service provider you appoint can handle operations.
The reference deployment runs as a Docker Compose stack on one machine; Ansible prepares installation and updates on Debian/Ubuntu. Internal encryption, observability and offline operation are available as additional layers. Kubernetes provides a separate deployment path; acceptance depends on the deployment mode.
Explore the architecture and technical details
01
Access
Console (SPA) · SQL worksheet · dashboards · AI assistant · MCP server — all behind one reverse proxy
02
Identity & governance
Keycloak OIDC · token exchange per RFC 8693 · row-access and masking policies · WORM audit · lineage
03
Compute
Trino under your identity · S, M and L workload classes in the Compose stack
04
Catalog & table format
Apache Iceberg with Nessie: ACID · time travel · branching · schema evolution · open to Spark, Flink, Trino
05
Storage & index
S3-compatible (MinIO, Ceph, NetApp StorageGRID, Dell ECS) · PostgreSQL with pgvector as the vector index
If you already know a cloud warehouse
The concepts stay, the bill changes. What is still missing says so.
- Proprietary table format
- Apache Iceberg with Nessie (open, versioned)
- Web interface for queries
- Console with SQL worksheet and data browser
- Roles and row filters
- Policies in Trino, under delegated identity
- Access history and provenance
- WORM audit log, lineage and access history
- Full-text and vector search
- Hybrid search with a local embedding model
- The vendor's AI features
- Pyro · AI in SQL · your choice of model
- Virtual warehouse
- Warehouse quotas and Kubernetes clusters
- Scheduled tasks
- Schedules for reports, threshold alerts and Iceberg maintenance
- Streams
- Table streams and PostgreSQL CDC
- Credit billing
- A fixed subscription
Cost
More questions. More AI. No credits per data query.
You choose where lavalake runs, the compute capacity you use and the terms you pay for it. Platform licensing follows active users and support, with no credits per data query. Budget infrastructure and operations using the costs of your chosen environment.
€3,000€300,000
No credits
A fixed subscription based on active users and support instead of query credits. Queries from people and agents use your compute capacity without metering each operation.
No egress
lavalake charges no egress fees on your data. Budget separately for your infrastructure, network connectivity and connected providers.
Hardware you already own
lavalake runs on your existing Kubernetes and your S3-compatible storage. Capacity you have already written off keeps earning.
Planning you can budget
Cost follows cluster size and term, not usage behavior. Your teams are free to explore the data again.
Monthly comparison
81% cheaperCloud warehouse today€45,000
lavalake on-premises€8,768
- lavalake subscription
- €1,250
- Hardware amortization
- €3,500
- Operations & administration
- €1,913
- Power, including cooling and losses
- €812
- Storage, network, redundancy, backup
- €1,294
Model assumption: 6 servers, 50 active users · Business
Review assumptions and costs →Savings over 3 years
€1,304,343
Model of recurring costs. We calculate migration, parallel operation, floor space and AI models separately for your setup.
Request a TCO analysisSources for context
roughly half
Andreessen Horowitz estimates that repatriating cloud workloads cuts total cost of ownership to about half. An estimate rather than a survey, and calculated for software companies at scale.
a16z, The Cost of Cloud, a Trillion Dollar Paradox, 2021$2 million a year
37signals published the breakdown of its cloud exit: $3.2 million in annual spend, then roughly $2 million less per year after $700K of hardware. A single case with real invoices — and not a data warehouse.
37signals, Cloud Exit, 2024–2025
Sovereignty
AI on sensitive data. With clear boundaries.
Giving AI access to business data means controlling permissions and where data goes. In lavalake, people and agents share the same access rules. You choose which model to connect: self-hosted on your network or with an external provider.
You choose where your AI runs
- The lakehouse and local search stay on your network; external AI providers receive conversation content and tool results used by the assistant
- The vendor has no access to content or metadata
- The embedding model runs locally; semantic search needs no cloud key
- Offline Compose installation and operation with local models
Provable, not asserted
- WORM audit log as a hash chain, over users and agents alike
- Lineage from source to reported figure, access history per table
- Every query under the identity of whoever is signed in — no shared service account
- Table and column classification with confirmed suggestions, without sending data values to the model
- Personal-data access, erasure and retention workflows
Operations
- Docker Compose for one machine, Ansible for installation and updates; Helm as the Kubernetes path
- Everything behind one reverse proxy; Trino and storage are unreachable from outside
- Daily database and configuration backup in the Compose stack; lakehouse files need separate backup
- Observability and Vault integration; HA profile awaits cluster acceptance
Use cases
AI and analytics where your data lives
From business knowledge to answers
Assistants find documents, query curated metrics and create dashboards. Your own agents can access these tools through MCP — under the user’s permissions, with actions recorded in the audit log.
Search, metrics and dashboards through MCP
Machine data and ERP in one analysis
Production telemetry meets SAP orders — without mirroring sensor data into a public cloud. Scrap analysis runs on the same cluster as financial controlling.
Analyze production and ERP data together
Risk calculation with auditable provenance
Regulatory reporting and risk models read from versioned Iceberg tables. Time travel reproduces any reporting date, and lineage answers the supervisor's question.
Trace historical data snapshots
Clinical analysis inside your own network
Treatment and billing data stay in-house, with analysis and AI assistance running on top. Roles and masking make sure each department sees only its own slice.
Masking applies in the engine, not in the interface
One metric instead of four exports
Store data comes into the lakehouse from the upstream systems, and replenishment and marketing compute on the same curated metrics of the semantic layer instead of each on its own extract.
One metric definition for every report
Making case management systems analyzable
Data from separate case management systems is brought together without leaving the legal framework. Operated in the state data center, analyzed by self-service.
Operated in the state data center
Migration
Four weeks, and your cloud subscription is last winter's problem
Migration here does not mean rebuilding. Tables come over as Iceberg, roles and permissions move into Keycloak and the Trino policies. Both systems run in parallel until the results reconcile.
- Week 1
Taking stock
We read your existing warehouse metadata: tables, views, roles, query history and cost distribution. The result is a migration plan with a defensible TCO calculation.
- Week 2
Installation
lavalake is installed on your cluster via Helm chart and wired to your S3-compatible storage, your AD and your monitoring. No new hardware purchase required.
- Week 3
Data and pipelines
Tables are taken over as Iceberg and queries are re-pointed at Trino. Both systems run in parallel until the results match row for row.
- Week 4
Cutover
BI connections point at lavalake, roles and row filters are in place, reports are validated against the old figures. Then the cloud subscription gets canceled.
Pricing
A fixed price that grows with your team
Every tier includes the complete platform: lakehouse, AI assistant, MCP server, search and governance. Tiers differ in the number of users and in support. Budget separately for external AI providers or your own models.
Your data can grow while your price stays put. It depends on active users alone – data volume, queries and server capacity play no part in the license.
Team
€249
License per month, up to 10 active users
The starting point for your data team: the complete platform, in production from day one.
- Iceberg lakehouse on your storage
- SQL worksheet, import assistant and dashboards
- MCP server, hybrid search and metrics
- Up to 10 active users
- Ticket support, answer within one business day
Growth
€549
License per month, up to 25 active users
For several departments working from the same data – finance, sales and procurement on one shared foundation.
- Everything in Team
- Up to 25 active users
- Ticket support, answer within one business day
Business
€1,250
License per month, up to 100 active users
For entire business units: one data platform for every site and team in the unit, with a committed support response time.
- Everything in Growth
- Up to 100 active users
- 8/5 support with a committed response time
Recommended
Enterprise
€2,499
License per month, unlimited users
The data platform for your entire company: every department, every site, as many users as you need – and your tickets come first.
- Everything in Business
- Unlimited users
- Priority handling of your tickets
Sovereign
Custom
License by agreement
For public authorities, critical infrastructure and regulated industries: source code escrow, on-site support and help with your certifications.
- Everything in Enterprise
- Offline operation with Compose
- Secret files for Compose; Vault/External Secrets for Kubernetes
- Source code escrow
- On-site engagements
- Help with your certifications
* Runs on your own servers – servers and compute are not included.
A single machine with 6 vCPU and 24 GB RAM already carries around 50 concurrent analysts on 60 million rows – measured in our documented load test. The measurements in detail
All prices net, excluding VAT. Every person who worked with data from lavalake in the last 30 days counts as active – directly or through connected tools such as Power BI or Tableau. People who only view dashboards and reports count as readers at 25 per cent: every 4 readers count as one user. If your team outgrows its tier, everything keeps running – we adjust the tier together.
Further reading
Read the docs
DocumentationInstall it, understand it, run it
From the first start on your own machine through the concepts to the switches that matter in production.
17 pages
BlogArticles on cost, data sovereignty and MCP
Why cloud warehouses get expensive, what sovereignty means technically, and why agents need a semantic layer.
17 articles
CalculatorWhat your cloud warehouse would cost in your own data center
A model from disclosed assumptions — each with a source or explicitly labelled an estimate, all adjustable.
10 assumptions, sourced one by one
See AI work with your business data.
In 30 minutes, we show how the assistant finds data, queries metrics and creates dashboards. Together, we discuss your preferred deployment, operations by your team or a service provider, your choice of model and the right access permissions.
- A live demo of the AI assistant and MCP tools
- Model choice, data flows and governance for your use case
- Next steps for a proof of concept in your environment