Release / / with v0.22.0
MCP Toolbox for Databases v0.23.0
Run MySQL-compatible tools against MariaDB.
Before you upgrade to v0.23.0
2 to fixMSSQL sources now supply default host and port values when omitted.
Read the evidence
Rename view input `viewname` to `view_name`; sequence fields `sequencename`, `schemaname`, and output `sequenceowner` become `sequence_name`, `schema_name`, and `sequence_owner`.
Schema listing now defaults to a maximum of 50 rows; set `limit` to request a different bound.
Read the evidence
Update response parsing for the added Cloud Console and Logging URLs in batch creation, listing, and retrieval outputs.
Read the evidence
What changed in v0.23.0
Adds Spark batch creation and database inspection tools; BigQuery numeric output becomes decimal strings. Adds MariaDB support and PostgreSQL statistics; Spark responses gain console and logging links.
Also: Also adds Spark batch creation, PostgreSQL statistics, and new output formats.
v0.23.0; use the release binaries or container image and configure the required source credentials. Beta release; the public API can change.
New things you can do
Run SQL and database inspection tools against MariaDB.
Read the evidence
Fixed and improved
Create Spark and PySpark batches.
Read the evidence
Inspect query statistics, column cardinality, publication tables, and tablespaces.
Read the evidence
List property graphs with the new graph-listing tool and prebuilt configuration.
Read the evidence
Clone Cloud SQL instances and run PostgreSQL pre-checks.
Read the evidence
Set `--allowed-origins`, attach tool annotations, and configure alternate access-token header names.
Read the evidence
Firebird sources are registered and can be loaded.
Read the evidence
Inspect table statistics, database statistics, settings, and roles; filter views by schema, schemas by owner, and indexes by unused status.
Read the evidence
Create dashboards with dashboard filters.
Read the evidence
Seeded by 