LabscoMCP early access ↗
MCP SERVER · OFFICIAL PROJECT

Spice.ai Data Runtime

SQL, search and sampling over your federated datasets — with the tool set defined by your own config.

by spice-ai ↗Relational SQL Databases✓ Official

LABSCO SUMMARY

The sampling tools are the ones that make an agent's SQL any good.

Handing a model a schema and asking for a query produces confident nonsense about columns whose values it has never seen. Distinct values, a random sample, a top-N — those three calls turn guessing into reading, and they cost a fraction of the failed queries they prevent. The registry meta-tools are the other thoughtful piece: past a certain size, listing every tool on every turn is the real cost of a data connection, and searching them instead is the correct fix.

What it is

Spice is a data runtime that federates your sources. Its endpoint is per project in Spice Cloud rather than a shared address, and the tools it exposes depend on what you configured.

What you get

  • Data — list_datasets, table_schema, sql, search
  • Sampling — sample_distinct_columns, random_sample, top_n_sample, which let an agent see the shape of a table before querying it
  • Runtime — get_readiness, get_current_datetime
  • Memory — load and store, plus websearch
  • Beyond a certain size the runtime switches to registry meta-tools, so a large tool set is searched rather than listed

Requirements

A project API key, not a personal access token. The runtime itself is open source under Apache 2.0; Spice Cloud is a subscription with usage-based pricing, and there is an enterprise route through AWS Marketplace. The open-source build sends anonymous telemetry by default.

Setup effort

Get your endpoint, then paste it — add your endpoint to your client with your key

See installation options