Databricks MCP Server

Read from the package source without running it. The installed server may list more.

• databricks_command_status

  Check the status and results of an executed command.

• databricks_create_appwrite action

  Create a new Databricks App.

• databricks_create_clusterwrite action

  Create a new compute cluster.

• databricks_create_connectionwrite action

  Create a new external connection.

• databricks_create_dashboardwrite action

  Create a new Lakeview dashboard.

• databricks_create_database_catalogwrite action

  Create a new catalog in a Lakebase database instance.

• databricks_create_database_instancewrite action

  Create a new Lakebase PostgreSQL database instance.

• databricks_create_database_tablewrite action

  Create a new table in a Lakebase database schema.

• databricks_create_execution_contextwrite action

  Create an execution context on a running cluster.

• databricks_create_experimentwrite action

  Create a new MLflow experiment.

• databricks_create_git_credentialwrite action

  Create a new Git credential for the current user.

• databricks_create_global_init_scriptwrite action

  Create a new global init script.

• databricks_create_instance_poolwrite action

  Create a new instance pool.

• databricks_create_runwrite action

  Create a new MLflow run within an experiment.

• databricks_dbfs_deletewrite action

  Delete a file or directory from DBFS.

• databricks_dbfs_download

  Download a file from DBFS and return its content as base64.

• databricks_dbfs_get_status

  Get the status and metadata of a single DBFS path.

• databricks_dbfs_list

  List files and directories at a DBFS path.

• databricks_dbfs_mkdirswrite action

  Create a directory in DBFS, including any necessary parent directories.

• databricks_dbfs_uploadwrite action

  Upload a file to DBFS from base64-encoded content.

• databricks_delete_appwrite action

  Delete a Databricks App.

• databricks_delete_connectionwrite action

  Delete an external connection.

• databricks_delete_database_instancewrite action

  Delete a Lakebase PostgreSQL database instance.

• databricks_delete_experimentwrite action

  Mark an MLflow experiment as deleted (soft delete).

• databricks_delete_git_credentialwrite action

  Delete a Git credential.

• databricks_delete_global_init_scriptwrite action

  Delete a global init script from the workspace.

• databricks_delete_instance_poolwrite action

  Delete an instance pool.

• databricks_delete_runwrite action

  Mark an MLflow run as deleted (soft delete).

• databricks_deploy_appwrite action

  Deploy source code to a Databricks App.

• databricks_destroy_execution_contextwrite action

  Destroy an execution context on a cluster.

• databricks_edit_cluster

  Edit the configuration of an existing compute cluster.

• databricks_execute_commandwrite action

  Execute a command in an existing execution context.

• databricks_files_create_directorywrite action

  Create a directory in a Unity Catalog Volume.

• databricks_files_deletewrite action

  Delete a file from a Unity Catalog Volume.

• databricks_files_download

  Download a file from a Unity Catalog Volume as base64-encoded content.

• databricks_files_get_metadata

  Get metadata for a file in a Unity Catalog Volume.

• databricks_files_list_directory

  List files and directories within a Unity Catalog Volume path.

• databricks_files_uploadwrite action

  Upload a file to a Unity Catalog Volume from base64-encoded content.

• databricks_generate_database_credential

  Generate temporary PostgreSQL credentials for Lakebase instances.

• databricks_genie_create_messagewrite action

  Send a follow-up message in an existing Genie conversation.

• databricks_genie_execute_message_querywrite action

  Re-execute the SQL query from a Genie message.

• databricks_genie_get_message

  Get a Genie message and its response.

• databricks_genie_get_message_query_result

  Get the SQL query result from a Genie message.

• databricks_genie_start_conversation

  Start a new Genie AI/BI conversation with a question.

• databricks_get_app

  Get detailed information about a specific Databricks App.

• databricks_get_app_deployment

  Get details of a specific app deployment.

• databricks_get_app_environment

  Get the environment configuration for a Databricks App.

• databricks_get_cluster

  Get detailed information about a specific compute cluster.

• databricks_get_connection

  Get detailed information about a specific connection.

• databricks_get_dashboard

  Get detailed information about a specific Lakeview dashboard.

• databricks_get_database_instance

  Get detailed information about a specific Lakebase database instance.

• databricks_get_effective_grants

  Get the effective (inherited + direct) permissions on a securable.

• databricks_get_experiment

  Get detailed information about a specific MLflow experiment.

• databricks_get_git_credential

  Get detailed information about a specific Git credential.

• databricks_get_global_init_script

  Get detailed information about a specific global init script.

• databricks_get_grants

  Get the permissions granted on a Unity Catalog securable.

• databricks_get_instance_pool

  Get detailed information about a specific instance pool.

• databricks_get_published_dashboard

  Get the published version of a Lakeview dashboard.

• databricks_get_runwrite action

  Get detailed information about a specific MLflow run.

• databricks_list_app_deployments

  List all deployments for a Databricks App.

• databricks_list_apps

  List all Databricks Apps in the workspace.

• databricks_list_artifacts

  List artifacts associated with an MLflow run.

• databricks_list_cluster_events

  List recent events for a compute cluster.

• databricks_list_cluster_policies

  List all cluster policies in the workspace.

• databricks_list_clusters

  List all compute clusters in the workspace.

• databricks_list_connections

  List all external connections in the workspace.

• databricks_list_dashboards

  List all Lakeview dashboards in the workspace.

• databricks_list_database_catalogs

  List all catalogs in a Lakebase database instance.

• databricks_list_database_instances

  List all Lakebase PostgreSQL database instances in the workspace.

• databricks_list_database_roles

  List all roles for a Lakebase database instance.

• databricks_list_database_tables

  List tables in a Lakebase database schema.

• databricks_list_experiments

  List MLflow experiments in the workspace.

• databricks_list_git_credentials

  List all Git credentials for the current user.

• databricks_list_global_init_scripts

  List all global init scripts in the workspace.

• databricks_list_instance_pools

  List all instance pools in the workspace.

• databricks_list_node_types

  List all available node types for compute clusters.

• databricks_list_spark_versions

  List all available Spark runtime versions.

• databricks_log_metric

  Log a metric value for an MLflow run.

• databricks_log_param

  Log a parameter for an MLflow run.

• databricks_migrate_dashboard

  Migrate a classic SQL dashboard to Lakeview format.

• databricks_pin_cluster

  Pin a compute cluster to prevent it from being auto-deleted.

• databricks_publish_dashboardwrite action

  Publish a Lakeview dashboard draft.

• databricks_resize_cluster

  Resize a running cluster to a different number of workers.

• databricks_restart_cluster

  Restart a running compute cluster.

• databricks_restore_experiment

  Restore a previously deleted MLflow experiment.

• databricks_search_experiments

  Search for MLflow experiments using filter expressions.

• databricks_search_runs

  Search for MLflow runs across one or more experiments.

• databricks_start_app

  Start a Databricks App.

• databricks_start_cluster

  Start a terminated compute cluster.

• databricks_stop_app

  Stop a running Databricks App.

• databricks_terminate_cluster

  Terminate a running compute cluster.

• databricks_tool_guide

  Find the right Databricks tools for a task or role.

• databricks_trash_dashboard

  Move a Lakeview dashboard to the trash.

• databricks_unpin_cluster

  Unpin a compute cluster, allowing it to be auto-deleted.

• databricks_unpublish_dashboard

  Unpublish a Lakeview dashboard.

• databricks_update_connectionwrite action

  Update an existing connection's options or name.

• databricks_update_dashboardwrite action

  Update an existing Lakeview dashboard draft.

• databricks_update_git_credentialwrite action

  Update an existing Git credential.

• databricks_update_global_init_scriptwrite action

  Update an existing global init script.

• databricks_update_runwrite action

  Update the status of an MLflow run.

• Code scan40 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 5 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

83/100

higher than 60% of 802 Databases servers

Tools

100

the typical Databases server has 8

Tools that change things

39%

typical: 10%. Fewer write tools means less an agent can break

Downloads a week

59

more than 45% of 324 Databases servers with a package

Databricks MCP Server: common questions

Is Databricks MCP Server safe?

Mostly: it is graded B (83/100). Read the Databricks MCP Server safety report

How do I install Databricks MCP Server?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Databricks MCP Server need an API key?

Yes. The registry entry asks for DATABRICKS_TOKEN.

Is Databricks MCP Server maintained?

The last commit was 40 days ago (2026-09-23). The latest release is v0.1.0.

What can I use instead of Databricks MCP Server?

Servers from other publishers that do the same job: GeoLens MCP server, DBHub MCP server and Keboola MCP server.

How does Databricks MCP Server compare with other Databases MCP servers?

safety score 83/100 (higher than 60% of 802 Databases servers); tools 100 (the typical Databases server has 8); tools that change things 39% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.