Database federation on Gyri connects ten database engines via live introspection — previewDbConnectorSchema discovers schema, installDbConnectorGraph wires db_operation bridges, and agents multihop across SQL rows, NoSQL documents, and CRM in one cited session.
Live schema introspection → storage:remote types → db_operation bridges. Query Postgres, SQLite, Redis, Elasticsearch, and cloud warehouses in the same multihop GraphQL session as CRM, docs, and public data.
Related: Integrations hub · Graph infrastructure · Federated search
Live schema introspection → storage:remote types → db_operation bridges. Query Postgres, SQLite, Redis, Elasticsearch, and cloud warehouses in the same multihop GraphQL session as CRM, docs, and public data.
information_schema introspection, FK-aware bridges, parameterized SELECT templates.
INFORMATION_SCHEMA columns and foreign keys mapped to remote graph types.
Embedded SQL — sqlite_master and PRAGMA introspection.
INFORMATION_SCHEMA for enterprise SQL Server databases.
Collection sampling and BSON type inference for document stores.
Partition/sort key discovery and safe GetItem/Scan/Query ops.
Cloud warehouse tables via INFORMATION_SCHEMA.
Dataset table discovery with service-account auth.
Index mapping introspection and term/match_all reads.
Keyspace prefix discovery via SCAN — GET and hash field reads.
query {
previewDbConnectorSchema(connectorId: "wdbc_…", typeKeyPrefix: "postgres")
}
previewDbConnectorSchema discovers tables, columns, primary keys, and foreign keys — agents configure exposure, not column shapes.
get_by_pk, list_rows, and filter_eq operations only. No raw SQL from GraphQL or agents. Read-only connectors with entity allowlists.
Join CRM deals, Slack threads, and Postgres rows in one cited GraphQL query — results land on custom records and insights.
federation-db-*-starter module packs for all 10 dialects with anchor types and FK bridges where supported.
Dashboards and SQL clients return tables — not cited, traversable nodes agents can join with CRM and docs.
One-off sync jobs break when schemas change. Introspection keeps the graph aligned with the source of truth.
Agents with raw SQL access are a liability. Gyri uses allowlisted tables and parameterized operation templates.
PostgreSQL, MySQL/MariaDB, SQLite, SQL Server, MongoDB, DynamoDB, Snowflake, BigQuery, Elasticsearch, and Redis — ten dialects with federation-db-*-starter module packs.
No. Only parameterized get_by_pk, list_rows, and filter_eq operations against allowlisted tables or collections.
previewDbConnectorSchema reads information_schema (SQL) or samples Mongo collections, then suggests remote types and FK bridges for installDbConnectorGraph.
Gyri federates into one graph. Agents orient with recall and ground, capture with reflect, and commit with promote — the full epistemic lifecycle via MCP think.
think verb=recallSemantic orient — load prior cited conclusions before you re-derive from scratch.
think verb=groundFTS-only orient on live federated CRM, email, and Slack — zero embed cost.
think verb=considerClassify novelty against the workspace corpus before you commit a thesis.
think verb=reflectCapture drafts, tensions, and questions as typed thoughts on the graph.
think verb=traverseMultihop GraphQL in one think call — deal → contact → email → ticket.
think verb=fetchHydrate full rows by ref when search or traverse surfaced the right node.
think verb=promoteGated commit — draft thought → durable cited insight the whole team recalls.
think verb=wishNatural-language buildout — queue workspace types, connectors, and workflows.
Full catalog via MCP think verb=catalog · Why Gyri think verbs beat API wrappers → · MCP for Claude & Cursor
Cross-links across product, think-verb guides, solutions, and native integrations — every page connects back to the Gyri agentic knowledge base.
Native connectors with cited search, Gyri think verbs, and MCP — browse all 65+