Databricks Connector for AI agents.
8 live capabilities
Manage your lakehouse and monitor data pipelines with your agent.
Waiting for input…
Why people use Databricks
Databricks for Monitoring Lakehouse Jobs
This Connector lets you stay in your current capability and just ask your agent to pull those logs. You get the exact failure point and status update in a few seconds, keeping your focus on fixing the code rather than hunting for the data.
What Vinkius changes
You get a direct line of communication between your AI agent and your Databricks workspace.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Troubleshooting a failed ETL
A data engineer asks the agent to show the last 5 runs for a specific job and then pull the error logs.
- Real-world use case 02
Auditing cluster capacity
A platform lead asks the agent to list all clusters and show the details for the ML training nodes.
- Real-world use case 03
Data discovery
An analyst asks the agent to list all catalogs and then find the schemas for the marketing database.
Complete set · 8capabilities
The complete Databricks capability set.
These are the exact actions your AI can choose when you ask it to work with Databricks.
01—04
4 capabilities in this set.
Part of 8 available through Databricks.
- 01 Capability
List warehouses
Enumerates all configured SQL Serverless warehouses. This lets you see your available compute resources.
- 02 Capability
List clusters
Lists all compute nodes in your workspace. Use this to see what's running and what's not.
- 03 Capability
Get cluster
Fetches specific details for a single cluster. This helps you audit health and capacity limits.
- 04 Capability
List jobs
Lists all configured workflows and jobs. Use this to see your entire pipeline lineup.
05—08
4 capabilities in this set.
Part of 8 available through Databricks.
- 05 Capability
List job runs
Lists the history of job executions. This is how you find out why a specific run failed.
- 06 Capability
List catalogs
Lists all root catalogs in the Unity Catalog. This is the first step to finding your data.
- 07 Capability
List schemas
Lists all schemas within a specific catalog. This helps you see your database structure quickly.
- 08 Capability
Get me
Retrieves the profile of the currently authenticated user. Use this to check your active permissions.
Set up in minutes
One URL. Then ask Databricks to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Databricks from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Databricks, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Databricks for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Databricks URL.
- Step 03
Save and start
Save the connection and enable Databricks in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"databricks": {
"url": "https://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Databricks
Open Agent mode in chat and ask: "Using Databricks, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"databricks": {
"url": "https://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Databricks
Ask Copilot: "Using Databricks, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"databricks": {
"url": "https://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Databricks
Open Cascade and ask: "Using Databricks, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"databricks": {
"url": "https://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Databricks
Ask Cline: "Using Databricks, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add databricks --transport http "https://edge.vinkius.com/vk_preview_aLUngwuWdCUusUCfiR78zXA9b27HYNx59jOLRy9C/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Databricks
Ask Claude: "Using Databricks, show me...". 8 tools are ready
Where the request belongs
Work Databricks can move forward.
This is for data professionals who spend their days navigating complex lakehouse environments and want to stop manual dashboard hunting.
Data Engineer
Checking job runs and cluster health without leaving the IDE.
Analytics Engineer
Verifying SQL warehouse availability and exploring schemas in real-time.
MLOps Engineer
Tracking model training jobs and auditing compute configurations.
Data Platform Team
Auditing workspace resources and verifying service principal identities.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsStarburst
Connect your AI to Starburst Enterprise. Query federated data lakes, manage access roles, and orchestrate complex data environments seamlessly.
Snowflake
Execute SQL queries, manage databases, and analyze data on Snowflake with AI agents.
Azure Synapse Analytics
Manage your Azure Synapse data pipelines seamlessly. audit Spark pools, SQL pools, datasets, and integration pipelines via your AI agent.
Amazon Redshift
Equip your AI to directly query, analyze, and manage your petabyte-scale data warehouse via the serverless AWS Redshift Data API.
StarRocks
High-performance analytical database. manage clusters, tables, and query data via AI.
Materialize (Streaming SQL DB)
Execute streaming SQL, manage compute clusters, and monitor real-time data pipelines directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Databricks connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Databricks.
The practical details behind the request, access and result.
Can the Databricks MCP help me find failed jobs?
Yes, it can list all your configured jobs and pull the execution history for specific runs. You can then ask your agent to show you the logs for any failed run to see exactly what went wrong.
Does the Databricks MCP work with the Unity Catalog?
It does. You can use it to list all root catalogs and drill down into specific schemas and databases to find your data without leaving your agent.
How does the Databricks MCP help with cluster management?
You can use it to see every compute cluster in your workspace at once. It also lets you pull detailed health and capacity information for any specific cluster.
Can I use the Databricks MCP to check my permissions?
Yes, the Connector can fetch your current profile information. This is useful for verifying your active permissions or checking a service principal's access levels.
Does the Databricks MCP support SQL warehouses?
Yes, it can enumerate all your configured SQL Serverless warehouses. This helps you keep track of your available SQL compute resources.
Can my agent check the status of a specific Databricks job run?
Yes. Provide the 'job_id' to the 'list_job_runs' capability. The agent will retrieve the chronological history of executions, allowing you to identify successful completions or precise points of failure in your workflows.
How do I explore schemas within a specific Unity Catalog via chat?
Use the 'list_schemas' capability and provide the catalog name. Your agent will pull the detailed databases and schemas registered inside that Unity Catalog, giving you immediate visibility into your data hierarchy.
Can I monitor the health of my Databricks clusters through the agent?
Absolutely. The 'list_clusters' and 'get_cluster' capabilities allow your agent to retrieve detailed node information and operational statuses, helping you audit cluster health and capacity across your workspace.
One connection away
Give your agent a direct line to Databricks.
Connect Databricks once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available