Databricks MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_MAX_RETRIES | No | Maximum number of API retries | 3 |
| DATABRICKS_HOST | Yes | Databricks workspace URL, e.g., https://your-workspace.databricks.com | |
| DATABRICKS_TOKEN | Yes | Databricks personal access token | |
| HTTP_TIMEOUT_SECONDS | No | HTTP client timeout in seconds | 60 |
| TOOL_TIMEOUT_SECONDS | No | Timeout for tool execution in seconds | 300 |
| DATABRICKS_WAREHOUSE_ID | No | Optional default SQL warehouse ID | |
| MAX_CONCURRENT_REQUESTS | No | Maximum number of concurrent requests | 8 |
| API_RETRY_BACKOFF_SECONDS | No | Retry backoff in seconds | 0.5 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/markov-kernel/databricks-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server