Skip to main content
Nimble brings the live web into the Databricks Lakehouse. Search, page extraction, site maps, crawls, and Web Search Agents sit alongside your Delta tables, Unity Catalog governance, and AI agents — so the AI you build inside Databricks can ground its answers in current external signal, not just historical data.
Nimble MCP: Agentic Web Search Platform listing on the Databricks Marketplace

​
Why web data belongs next to the Lakehouse

Databricks is great at orchestrating the data you already own. But the world your data describes lives outside the Lakehouse, and most of the questions stakeholders actually ask need both. Nimble closes that gap without leaving the Databricks ecosystem:
  • Enrich Delta tables in place. Pull current company metadata, product details, or pricing for the rows in a Unity Catalog table, and land the results straight back as a governed Delta table.
  • Ground agents in live signal. Give a Databricks-hosted agent the same Nimble tools you’d use yourself, so it can research, verify, and gather external context as part of its workflow.
  • Govern every web call. Route Nimble through Unity AI Gateway so every request inherits Databricks-native audit, lineage, and access control.
  • Stay in SQL. Call Nimble as table functions inside any SELECT, so notebooks, dashboards, dbt models, Workflows, and Genie consume the output transparently.

​
Pick a surface

https://mintcdn.com/nimble-f5a8283f/Uhf7Z1PiT7svxqB6/images/icons/marketplace.svg?fit=max&auto=format&n=Uhf7Z1PiT7svxqB6&q=85&s=191b84babb9cab993af0752de8319173

Marketplace & MCP

Install Nimble MCP Server from the Databricks Marketplace as a one-click Unity Catalog connection. Govern it with Unity AI Gateway, then test it in AI Playground and Databricks Assistant. The install foundation every other surface builds on.
https://mintcdn.com/nimble-f5a8283f/DGpFmwiXECVJsQZd/images/icons/genie.svg?fit=max&auto=format&n=DGpFmwiXECVJsQZd&q=85&s=8d72152137e59e24bbd073428ea05d87

Genie One

Ask the live web in plain English from Genie One. Enable the Nimble MCP connection and business users get cited, web-grounded answers — no SQL, no notebook. The natural-language surface for the whole integration.
https://mintcdn.com/nimble-f5a8283f/11o25xfLHwYX_BgD/images/icons/data-enrichment.svg?fit=max&auto=format&n=11o25xfLHwYX_BgD&q=85&s=90ace12188af8758c7f439576d0d6a66

Data Enrichment

Call Nimble as SQL-native table functions in Unity Catalog. nimble_search, nimble_extract, and nimble_agent_run run live web data inside a SELECT and land results in governed Delta tables — dbt-native, Workflow-native, Genie-native.

​
When to use which surface

The Databricks integration spans three surfaces over one Nimble connection. Pick by question:
You want to…UsePage
Give an agent, AI Playground, or Databricks Assistant live web tools through a governed MCP connectionMarketplace & MCP installMarketplace & MCP
Let a business user ask live-web questions in plain English and get cited answersGenie One + the Nimble MCP connectionGenie One
Enrich N warehouse rows with structured web fields, or land web data in Delta tables — in pure SQLnimble_search / nimble_extract / nimble_agent_run table functionsData Enrichment
All three share the same Nimble platform underneath — the difference is who drives the calls: an LLM agent (MCP), a business user in natural language (Genie), or your SQL pipeline (table functions).

​
Resources

Databricks Marketplace Listing

Install Nimble MCP Server directly from the Marketplace

Nimble MCP Server Docs

Full MCP Server setup for Cursor, Claude, and other clients

Databricks External MCP Docs

Databricks documentation for external MCP server connections

Nimble Web Search Agents

Overview of WSAs — what they are, when to use them, how they parse