Skip to main content
oleander exposes a remote MCP server and a CLI that agents can use to query, run, and reason about your data infrastructure without leaving the editor. Wire either one up once and your agent gains the full context of your lake:
  • Tables and catalogs
  • Run history and lineage
  • Costs, logs, and traces

What agents can do

With the MCP server connected, an agent can:
  • Query your Iceberg lake tables directly with SQL
  • Upload and submit Spark jobs, then monitor their progress
  • Pull run lineage, cost breakdowns, and logs for any pipeline execution
  • Discover and inspect catalog tables and schemas
  • Investigate failures and surface downstream impact before shipping a change
A common pattern is building or debugging a data pipeline end to end from the editor: the agent reads from your lake, writes a transformation, submits it, then verifies the output and lineage without you switching contexts.

Cost-aware compute routing

oleander exposes DuckDB, Spark, and Polars through the MCP. An agent can choose the right engine for the job: DuckDB for fast, cheap ad hoc queries, Polars for DataFrame workloads, and Spark for large-scale processing. Because the agent sees cost per run, it can suggest or automatically prefer the lower-cost option for a given workload and scale up only when needed.

Install

claude mcp add --transport http oleander https://oleander.dev/mcp
Authenticate via the OAuth flow when prompted. See Claude Code setup for details.

How it works

Both the MCP server and CLI authenticate with your oleander API key. The MCP server runs remotely at https://oleander.dev/mcp and streams tool results back to your agent over the Model Context Protocol. The CLI is a local binary that talks to the same API. Use the MCP when working interactively with a coding agent. Use the CLI when scripting, automating, or running from a pipeline.