Databricks Integration
Live

Lakehouse & notebooks
on a live graph.

Databricks workspace metadata and notebook context federated with Snowflake, CRM, and product analytics — lakehouse lineage traverses the graph for cited BI and GTM intelligence.

Start free trial All integrations
Federation path

Databricks joins
your full stack.

Databricks
Gyri graph
CRM · comms · docs
What connects

Databricks data
in your graph.

Data

Catalog & schemas

Data

Notebooks & jobs

Data

Cluster metadata

Data

Unity Catalog grants

The problem

Databricks alone
is not enough.

01

Lakehouse siloed from GTM

Databricks holds analytics pipelines — but deal context and product signals live in CRM and Slack without cited joins.

02

Manual metric pulls

Analysts export Databricks job outputs before every review instead of federated cited synthesis on the graph.

03

No agent-ready data context

Databricks notebooks cannot multihop to Mixpanel events, CRM pipeline, and institutional insights in one answer.

With Gyri

Federated, cited,
agent-ready.

Lakehouse federation

Pipelines on the graph

Databricks catalog and job metadata index alongside Snowflake and Segment for federated search.

Cross-source joins

Metric → account → comms

Multihop queries link Databricks KPIs to HubSpot accounts and Slack threads with citations.

BI + GTM

Lakehouse joins pipeline

Federate Databricks revenue models with Stripe MRR and cited institutional forecast insights.

MCP agents

Agents read lakehouse context

Claude and Cursor traverse cited Databricks metadata on the same graph as analytics and RevOps teams.

Gyri think verbs

26 MCP think verbs —
not API wrappers.

Databricks 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=recall

Semantic orient — load prior cited conclusions before you re-derive from scratch.

think verb=ground

FTS-only orient on live federated CRM, email, and Slack — zero embed cost.

think verb=consider

Classify novelty against the workspace corpus before you commit a thesis.

think verb=reflect

Capture drafts, tensions, and questions as typed thoughts on the graph.

think verb=traverse

Multihop GraphQL in one think call — deal → contact → email → ticket.

think verb=fetch

Hydrate full rows by ref when search or traverse surfaced the right node.

think verb=promote

Gated commit — draft thought → durable cited insight the whole team recalls.

think verb=wish

Natural-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

Use cases

Built for
GTM operators.

Board metrics brief

Join Databricks revenue notebooks with CRM pipeline and cited variance explanations — exec summary.

Account health

Correlate Databricks usage tables with support ticket themes and product analytics signals.

Pipeline lineage

Link Databricks job definitions to Notion metric docs and cited institutional definitions.

Works with

Federate alongside
native connectors.

HubSpot
Slack
Notion
Pipedrive
Setup

Connect in
minutes.

Databricks personal access token and workspace URL in Settings → Integrations.

1. Start a free trial at app.gyri.io · 2. Open Settings → Integrations · 3. Run your first federated query with cited answers.

Connect Databricks Setup guide

Connect Databricks to Gyri.

Free trial — workspace token, cited federated lakehouse context.

Start free trial Browse integrations