# The Multi-Engine Data Warehouse for Agents & Builders

> The multi-engine data warehouse for agents & builders. Drop your data in and any agent can search, query, and build with it. Nothing to set up, no surprise bills.
> Source: https://oleander.dev/

Your queries deserve to run on the right tool. Our intelligent query routing translates and distributes your query to the most efficient available engine so you can move fast without burning all of your cash.

- Start here: https://oleander.dev/account
- Agent setup guide: https://oleander.dev/install.md
- Documentation: https://docs.oleander.dev
- Pricing: https://oleander.dev/pricing.md
- Site index for agents: https://oleander.dev/llms.txt

## Connect an agent

There is one MCP endpoint for everything, on streamable HTTP with OAuth sign-in on first use:

```
https://oleander.dev/mcp
```

```sh
claude mcp add --transport http oleander https://oleander.dev/mcp
codex mcp add oleander --url https://oleander.dev/mcp
opencode mcp add oleander --url https://oleander.dev/mcp
```

Full per-client instructions, including Cursor and VS Code, are in the [agent setup guide](https://oleander.dev/install.md).

## Instant fully managed storage and compute

Launch and query your new data warehouse in under 5 minutes.

- **Zero-Ops.** No data team needed; zero-maintenance and lightweight. See the [quickstart](https://docs.oleander.dev/quickstart).
- **Right-Sized Compute.** Save money on small datasets; ramp up the horsepower when you need it. See [Bloom](https://docs.oleander.dev/platform/compute/bloom).
- **Intelligent Query Routing.** Let oleander translate and route every query to the right compute engine. See [query routing](https://docs.oleander.dev/platform/query-routing/overview).
- **Plug and Play.** Seamlessly add engines to your stack, oleander grows with you. See [catalogs](https://docs.oleander.dev/platform/storage/catalogs).

## Built for agents

Teams build faster with ai-first tooling. oleander empowers your agents with infrastructure built for them.

- **[Native Agent Plugins](https://docs.oleander.dev/mcp/claude).** Install our plugins for Claude + Codex so your agent can directly query your business data.
- **[Universal MCP](https://docs.oleander.dev/mcp/introduction).** Connect our universal MCP to your favorite agent.
- **[Guardrails](https://docs.oleander.dev/mcp/protocol).** Prevent your agent from spontaneously clearing up a bunch of "free" space, cross joining all of your largest tables, and generally being a menace.
- **[Remediation Tooling](https://docs.oleander.dev/platform/observability/alerts).** Tools like automatic anomaly investigation and instant RCA boost your agent.

## Managed and supported tools

oleander's intelligent query routing means that you can use one, two, or all of these options without needing to be a database expert.

### Storage

| Catalog                   | Fully managed | Bring your own |
| ------------------------- | ------------- | -------------- |
| Managed Iceberg           | Yes           | N/A            |
| Snowflake Horizon Catalog | No            | Yes            |
| AWS Glue Data Catalog     | No            | Yes            |
| Iceberg REST Catalog      | No            | Yes            |

### Compute engines

| Engine     | Execution                  | Fully managed | Bring your own |
| ---------- | -------------------------- | ------------- | -------------- |
| Bloom      | Adaptive                   | Yes           | N/A            |
| DuckDB     | Single-node                | Yes           | Yes            |
| Polars     | Single-node / Distributed* | Yes           | Yes            |
| Spark      | Distributed                | Yes           | Yes            |
| Snowflake  | External                   | N/A           | Yes            |
| Databricks | External                   | N/A           | Yes            |

\* Distributed Polars is available for larger workloads.

## Query from where you work best

Beyond our UI, our tooling allows you to query oleander wherever you are.

- **SDK.** A unified SDK allows you to query your data straight from code.
- **CLI.** Use our command-line interface for querying and managing data from infrastructure or your terminal.
- **MCP.** Connect our native interface for agents to query your data with built-in routing and governance.

## Designed to scale

Launch your oleander warehouse with a team of one, keep expanding it after you reach 1000 employees.

### Observe

- **Lineage.** Robust lineage for all of your queries, datasets, and transformations powered by OpenLineage.
- **SQL telemetry.** Query pre-structured telemetry data using SQL.
- **From the first query.** Automated observability starting with your first query, so no history is lost.

### Govern

- **Sensitive data.** Lineage-powered governance makes tracing sensitive data easier than ever.
- **Environments.** Multi-engine routing allows for easy separation of environments.
- **Permissions.** Manage permissions on a user or agent level.

### Grow

- **Engines.** Expand your ecosystem with a virtually unlimited number of engines.
- **Compute.** Configure heavier compute as your data grows.
- **External sources.** Add a growing number of external sources, including Snowflake, to your oleander targets.

## More

- [Product](https://oleander.dev/product.md)
- [Pricing](https://oleander.dev/pricing.md)
- [Blog](https://oleander.dev/blog)
- [Growing Tips: Apache Iceberg & Spark 101](https://oleander.dev/grow)
- [Parquet viewer](https://oleander.dev/parquet), [OpenLineage validator](https://oleander.dev/ol-validate), [lineage graph playground](https://oleander.dev/ol-graph)