Connect AI agents to Databricks Workspace

Scalekit connector

The Databricks Workspace connector lets your AI agent work with Databricks Workspace. You connect it once with a service principal, and Scalekit authenticates every call, so your agent never handles credentials. It comes with 53 tools.

Tools: 53
What they doRead · write · destructive: 28 · 18 · 728 read18 write7 destructive
Users sign in with: Service account

What you can do

Run SQL queries: execute SQL on a SQL warehouse, fetch results, and cancel running statements
Explore data: browse Unity Catalog catalogs, schemas, tables, and columns, including key constraints
Manage jobs: create and delete jobs, trigger runs, and check run status and results
Manage clusters and warehouses: create, resize, start, restart, and terminate clusters, and start or stop SQL warehouses
Work with notebooks and files: list, import, export, and delete notebooks, and read or write files in DBFS
Manage repos and secrets: clone Git repos, switch branches, and store secrets in secret scopes

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Databricks Workspace connection
In AgentKit > Connections, create a Databricks Workspace connection. The name you give it is the connection_name your code passes. See Configure connections.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

databricksworkspace_cluster_getGet details of a specific Databricks cluster by cluster ID.Read-only
Get Cluster
Get details of a specific Databricks cluster by cluster ID.
Inputs
cluster_idstringrequired
The unique identifier of the cluster.
databricksworkspace_clusters_listList all clusters in the Databricks workspace.Read-only
List Clusters
List all clusters in the Databricks workspace.
Inputs
This tool takes no inputs.
databricksworkspace_dbfs_listList the contents of a directory on the Databricks File System (DBFS).Read-only
List DBFS Directory
List the contents of a directory on the Databricks File System (DBFS).
Inputs
pathstringrequired
The DBFS path to list.
databricksworkspace_dbfs_readRead up to 1 MB of a file's contents from the Databricks File System (DBFS).Read-only
Read DBFS File
Read up to 1 MB of a file's contents from the Databricks File System (DBFS). The response returns the content base64-encoded. Use offset and length to page through larger files.
Inputs
pathstringrequired
The DBFS path of the file to read.
lengthinteger
Number of bytes to read, starting at offset. Maximum is 1,048,576 (1 MB).
offsetinteger
Byte offset to start reading from.
databricksworkspace_information_schema_columnsList columns for a table using INFORMATION_SCHEMA.COLUMNS.Read-only
List Columns (INFORMATION_SCHEMA)
List columns for a table using INFORMATION_SCHEMA.COLUMNS. Returns column name, data type, nullability, numeric precision/scale, max char length, and comment.
Inputs
catalogstringrequired
The catalog containing the table.
schemastringrequired
The schema containing the table.
tablestringrequired
The table to list columns for.
warehouse_idstringrequired
The ID of the SQL warehouse to run the query on.
databricksworkspace_information_schema_schemataList all schemas within a catalog using INFORMATION_SCHEMA.SCHEMATA.Read-only
List Schemas (INFORMATION_SCHEMA)
List all schemas within a catalog using INFORMATION_SCHEMA.SCHEMATA. Used for schema discovery during setup.
Inputs
catalogstringrequired
The catalog to list schemas from.
warehouse_idstringrequired
The ID of the SQL warehouse to run the query on.
databricksworkspace_information_schema_table_constraintsList PRIMARY KEY and FOREIGN KEY constraints for tables in a schema using INFORMATION_SCHEMA.TABLE_CONSTRAINTS.Read-only
List Table Constraints (INFORMATION_SCHEMA)
List PRIMARY KEY and FOREIGN KEY constraints for tables in a schema using INFORMATION_SCHEMA.TABLE_CONSTRAINTS. Used to auto-detect join keys.
Inputs
catalogstringrequired
The catalog containing the schema.
schemastringrequired
The schema to list constraints from.
warehouse_idstringrequired
The ID of the SQL warehouse to run the query on.
databricksworkspace_information_schema_tablesList tables and views in a schema using INFORMATION_SCHEMA.TABLES.Read-only
List Tables (INFORMATION_SCHEMA)
List tables and views in a schema using INFORMATION_SCHEMA.TABLES. Returns table name, type (MANAGED, EXTERNAL, VIEW, etc.), and comment for schema discovery.
Inputs
catalogstringrequired
The catalog to query INFORMATION_SCHEMA from.
schemastringrequired
The schema to list tables from.
warehouse_idstringrequired
The ID of the SQL warehouse to run the query on.
databricksworkspace_job_getGet details of a specific Databricks job by job ID.Read-only
Get Job
Get details of a specific Databricks job by job ID.
Inputs
job_idintegerrequired
The unique identifier of the job.
databricksworkspace_job_run_getRetrieve the metadata and status of a single Databricks job run, including its state, start/end times, and task results.Read-only
Get Job Run
Retrieve the metadata and status of a single Databricks job run, including its state, start/end times, and task results. Complements databricksworkspace_job_runs_list, which only lists summaries.
Inputs
run_idstringrequired
The ID of the job run to retrieve.
databricksworkspace_job_runs_listList all job runs in the Databricks workspace, optionally filtered by job ID.Read-only
List Job Runs
List all job runs in the Databricks workspace, optionally filtered by job ID.
Inputs
job_idinteger
Filter runs by a specific job ID. If omitted, returns runs for all jobs.
limitinteger
The number of runs to return. Defaults to 20. Maximum is 1000.
offsetinteger
The offset of the first run to return.
databricksworkspace_jobs_listList all jobs in the Databricks workspace.Read-only
List Jobs
List all jobs in the Databricks workspace.
Inputs
limitinteger
The number of jobs to return. Defaults to 20. Maximum is 100.
offsetinteger
The offset of the first job to return.
databricksworkspace_permissions_getRetrieve the access control list (permissions) for a Databricks object such as a cluster, job, notebook, or SQL warehouse.Read-only
Get Object Permissions
Retrieve the access control list (permissions) for a Databricks object such as a cluster, job, notebook, or SQL warehouse.
Inputs
request_object_idstringrequired
The ID of the object to retrieve permissions for.
request_object_typestringrequired
The type of object to retrieve permissions forone of clustersdirectoriesjobsnotebooksregistered-modelswarehouses
databricksworkspace_repos_listList Git repositories linked into the Databricks workspace, optionally filtered by path prefix.Read-only
List Repos
List Git repositories linked into the Databricks workspace, optionally filtered by path prefix.
Inputs
next_page_tokenstring
Token for the next page of results
path_prefixstring
Filter repos to only those whose workspace path starts with this prefix
databricksworkspace_scim_me_getRetrieve information about the currently authenticated service principal in the Databricks workspace.Read-only
Get Current Service Principal
Retrieve information about the currently authenticated service principal in the Databricks workspace.
Inputs
This tool takes no inputs.
databricksworkspace_scim_users_listList all users in the Databricks workspace using the SCIM v2 API.Read-only
List Users
List all users in the Databricks workspace using the SCIM v2 API.
Inputs
countinteger
Maximum number of results to return per page.
filterstring
SCIM filter expression to narrow results (e.g. userName eq "user@example.com").
startIndexinteger
1-based index of the first result to return. Used for pagination.
databricksworkspace_secrets_listList the secret keys stored within a Databricks secret scope.Read-only
List Secrets
List the secret keys stored within a Databricks secret scope. Only key names and metadata are returned, never secret values.
Inputs
scopestringrequired
The name of the secret scope to list keys from.
databricksworkspace_secrets_scopes_listList all secret scopes available in the Databricks workspace.Read-only
List Secret Scopes
List all secret scopes available in the Databricks workspace.
Inputs
This tool takes no inputs.
databricksworkspace_sql_statement_getGet the status and results of a previously executed SQL statement by its statement ID.Read-only
Get SQL Statement Status
Get the status and results of a previously executed SQL statement by its statement ID.
Inputs
statement_idstringrequired
The ID of the SQL statement to retrieve.
databricksworkspace_sql_statement_result_chunk_getFetch a specific result chunk for a paginated SQL statement result.Read-only
Get SQL Statement Result Chunk
Fetch a specific result chunk for a paginated SQL statement result. Use when a statement result has multiple chunks (large result sets).
Inputs
chunk_indexintegerrequired
The index of the result chunk to fetch (0-based).
statement_idstringrequired
The ID of the SQL statement.
databricksworkspace_sql_warehouse_getGet details of a specific Databricks SQL warehouse by its ID.Read-only
Get SQL Warehouse
Get details of a specific Databricks SQL warehouse by its ID.
Inputs
warehouse_idstringrequired
The ID of the SQL warehouse to retrieve.
databricksworkspace_sql_warehouses_listList all SQL warehouses available in the Databricks workspace.Read-only
List SQL Warehouses
List all SQL warehouses available in the Databricks workspace.
Inputs
This tool takes no inputs.
databricksworkspace_unity_catalog_catalogs_listList all Unity Catalogs accessible to the service principal in the Databricks workspace.Read-only
List Unity Catalogs
List all Unity Catalogs accessible to the service principal in the Databricks workspace.
Inputs
This tool takes no inputs.
databricksworkspace_unity_catalog_schemas_listList all schemas within a Unity Catalog in the Databricks workspace.Read-only
List Unity Catalog Schemas
List all schemas within a Unity Catalog in the Databricks workspace.
Inputs
catalog_namestringrequired
The name of the catalog to list schemas from.
databricksworkspace_unity_catalog_tables_listList all tables and views within a schema in a Unity Catalog in the Databricks workspace.Read-only
List Unity Catalog Tables
List all tables and views within a schema in a Unity Catalog in the Databricks workspace.
Inputs
catalog_namestringrequired
The name of the catalog containing the schema.
schema_namestringrequired
The name of the schema to list tables from.
databricksworkspace_workspace_exportExport a Databricks notebook or directory.Read-only
Export Workspace Object
Export a Databricks notebook or directory. Directories can only be exported as DBC archives. The response contains the content base64-encoded.
Inputs
pathstringrequired
The absolute workspace path of the notebook or directory to export.
formatstring
Export format for the objectone of DBCHTMLJUPYTERSOURCEdefault SOURCE
databricksworkspace_workspace_get_statusGet metadata about a Databricks workspace object (notebook, folder, or file), including its object type, language, and object ID.Read-only
Get Workspace Object Status
Get metadata about a Databricks workspace object (notebook, folder, or file), including its object type, language, and object ID.
Inputs
pathstringrequired
The absolute workspace path of the object.
databricksworkspace_workspace_listList the contents (notebooks, folders, libraries) of a Databricks workspace directory.Read-only
List Workspace Objects
List the contents (notebooks, folders, libraries) of a Databricks workspace directory.
Inputs
pathstringrequired
The absolute workspace path to list.
databricksworkspace_cluster_createCreate and start a new Databricks compute cluster.Write
Create Cluster
Create and start a new Databricks compute cluster. Specify either a fixed number of workers or an autoscaling range.
Inputs
cluster_namestringrequired
Display name for the new cluster
node_type_idstringrequired
The instance type for driver and worker nodes
spark_versionstringrequired
The Databricks Runtime version to use for the cluster
autotermination_minutesinteger
Automatically terminate the cluster after this many minutes of inactivity. Set to 0 to disable.default 60
max_workersinteger
Maximum number of workers when autoscaling. Provide with min_workers instead of num_workers.
min_workersinteger
Minimum number of workers when autoscaling. Provide with max_workers instead of num_workers.
num_workersinteger
Fixed number of worker nodes. Omit and use min_workers/max_workers instead to enable autoscaling.
databricksworkspace_cluster_editEdit the configuration of an existing Databricks cluster.Write
Edit Cluster
Edit the configuration of an existing Databricks cluster. The cluster must be running or terminated; this replaces its full configuration, so include every field you want to keep, not just the ones you're changing.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to edit.
cluster_namestringrequired
Display name for the cluster
node_type_idstringrequired
The instance type for driver and worker nodes
spark_versionstringrequired
The Databricks Runtime version to use for the cluster
autotermination_minutesinteger
Automatically terminate the cluster after this many minutes of inactivity. Set to 0 to disable.default 60
max_workersinteger
Maximum number of workers when autoscaling. Provide with min_workers instead of num_workers.
min_workersinteger
Minimum number of workers when autoscaling. Provide with max_workers instead of num_workers.
num_workersinteger
Fixed number of worker nodes. Omit and use min_workers/max_workers instead to enable autoscaling.
databricksworkspace_cluster_resizeResize a running Databricks cluster by setting a fixed worker count or an autoscaling range.Write
Resize Cluster
Resize a running Databricks cluster by setting a fixed worker count or an autoscaling range.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to resize.
max_workersinteger
Maximum number of workers when autoscaling. Provide with min_workers instead of num_workers.
min_workersinteger
Minimum number of workers when autoscaling. Provide with max_workers instead of num_workers.
num_workersinteger
Fixed number of worker nodes. Omit and use min_workers/max_workers instead to enable autoscaling.
databricksworkspace_cluster_restartRestart a running Databricks cluster by cluster ID.Write
Restart Cluster
Restart a running Databricks cluster by cluster ID. Useful for clearing cached state or applying updated init scripts.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to restart.
databricksworkspace_cluster_startStart a terminated Databricks cluster by cluster ID.Write
Start Cluster
Start a terminated Databricks cluster by cluster ID.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to start.
databricksworkspace_dbfs_putWrite a small file (up to 2 MB) to the Databricks File System (DBFS) in a single call, creating any needed parent directories.Write
Write DBFS File
Write a small file (up to 2 MB) to the Databricks File System (DBFS) in a single call, creating any needed parent directories. For larger files, use the streaming create/add-block/close APIs instead.
- Idempotent
Inputs
contents_base64stringrequired
Base64-encoded file contents to write. Maximum 2 MB after encoding.
pathstringrequired
The DBFS path to write the file to.
overwriteboolean
Whether to overwrite an existing file at the destination pathdefault false
databricksworkspace_job_createCreate a new Databricks job definition made up of one or more tasks.Write
Create Job
Create a new Databricks job definition made up of one or more tasks.
Inputs
namestringrequired
Display name for the new job
tasksarrayrequired
Array of task definitions that make up the job. Each task needs a unique task_key plus one task type (notebook_task, spark_jar_task, python_wheel_task, sql_task, etc.) and either existing_cluster_id or new_cluster.
job_clustersarray
Shared cluster definitions that tasks can reference by job_cluster_key instead of using existing_cluster_id or new_cluster per task
max_concurrent_runsinteger
Maximum number of concurrent runs allowed for this job
tagsobject
Key-value tags attached to the job
timeout_secondsinteger
Timeout applied to each run of this job
databricksworkspace_job_run_nowTrigger an immediate run of a Databricks job by job ID.Write
Trigger Job Run
Trigger an immediate run of a Databricks job by job ID.
Inputs
job_idintegerrequired
The unique identifier of the job to run.
databricksworkspace_permissions_updateUpdate the access control list (permissions) for a Databricks object such as a cluster, job, notebook, or SQL warehouse.Write
Update Object Permissions
Update the access control list (permissions) for a Databricks object such as a cluster, job, notebook, or SQL warehouse. Existing grants not included in the access control list are preserved unless explicitly overridden.
- Idempotent
Inputs
access_control_listarrayrequired
JSON array of access control entries to apply. Each entry has one grantee key (user_name, group_name, or service_principal_name) and a permission_level.
request_object_idstringrequired
The ID of the object to update permissions for.
request_object_typestringrequired
The type of object to update permissions forone of clustersdirectoriesjobsnotebooksregistered-modelswarehouses
databricksworkspace_repo_createClone a Git repository into the Databricks workspace.Write
Create Repo
Clone a Git repository into the Databricks workspace.
Inputs
providerstringrequired
The Git provider hosting the repositoryone of awsCodeCommitazureDevOpsServicesbitbucketCloudbitbucketServergitHubgitHubEnterprisegitLabgitLabEnterpriseEdition
urlstringrequired
The HTTPS clone URL of the Git repository
pathstring
Desired workspace path for the cloned repo. If omitted, Databricks places it under /Repos/{user}/{repo name}.
databricksworkspace_repo_updateCheck out a different branch or tag in a Databricks repo, or pull the latest changes for the currently checked-out branch.Write
Update Repo
Check out a different branch or tag in a Databricks repo, or pull the latest changes for the currently checked-out branch.
- Idempotent
Inputs
repo_idstringrequired
The ID of the repo to update.
branchstring
Name of the branch to check out. Provide either branch or tag, not both.
tagstring
Name of the tag to check out. Provide either branch or tag, not both.
databricksworkspace_secret_putCreate or overwrite a secret in a Databricks secret scope.Write
Put Secret
Create or overwrite a secret in a Databricks secret scope. Provide exactly one of string_value or bytes_value (base64-encoded).
- Idempotent
Inputs
keystringrequired
The key name under which to store the secret.
scopestringrequired
The name of the secret scope to write the secret into.
bytes_valuestring
Base64-encoded bytes value to store. Use instead of string_value.
string_valuestring
The UTF-8 string value to store. Use instead of bytes_value.
databricksworkspace_secret_scope_createCreate a new secret scope in the Databricks workspace, backed by Databricks or an Azure Key Vault.Write
Create Secret Scope
Create a new secret scope in the Databricks workspace, backed by Databricks or an Azure Key Vault.
Inputs
scopestringrequired
Name of the new secret scope.
backend_azure_keyvaultobject
Azure Key Vault connection details. Required when scope_backend_type is AZURE_KEYVAULT.
initial_manage_principalstring
The initial principal granted MANAGE permission on this scope. Only 'users' is supported for Databricks-backed scopes.
scope_backend_typestring
The backend used to store the scope's secretsone of DATABRICKSAZURE_KEYVAULT
databricksworkspace_sql_statement_cancelCancel a running SQL statement by its statement ID.Write
Cancel SQL Statement
Cancel a running SQL statement by its statement ID.
- Idempotent
Inputs
statement_idstringrequired
The ID of the SQL statement to cancel.
databricksworkspace_sql_statement_executeExecute a SQL statement on a Databricks SQL warehouse and return the results.Write
Execute SQL Statement
Execute a SQL statement on a Databricks SQL warehouse and return the results.
Inputs
statementstringrequired
The SQL statement to execute.
warehouse_idstringrequired
The ID of the SQL warehouse to execute the statement on.
catalogstring
The catalog to use for the statement execution.
schemastring
The schema to use for the statement execution.
databricksworkspace_sql_warehouse_startStart a stopped Databricks SQL warehouse by its ID.Write
Start SQL Warehouse
Start a stopped Databricks SQL warehouse by its ID.
Inputs
warehouse_idstringrequired
The ID of the SQL warehouse to start.
databricksworkspace_sql_warehouse_stopStop a running Databricks SQL warehouse by its ID.Write
Stop SQL Warehouse
Stop a running Databricks SQL warehouse by its ID.
Inputs
warehouse_idstringrequired
The ID of the SQL warehouse to stop.
databricksworkspace_workspace_importImport a notebook into the Databricks workspace from base64-encoded content.Write
Import Workspace Object
Import a notebook into the Databricks workspace from base64-encoded content. Can also be used to create a notebook from source text.
- Idempotent
Inputs
content_base64stringrequired
Base64-encoded content of the notebook to import.
pathstringrequired
The absolute workspace path to import the notebook to.
formatstring
Format of the content being importedone of DBCHTMLJUPYTERSOURCEdefault SOURCE
languagestring
Programming language of the notebook, required when format is SOURCEone of PYTHONRSCALASQL
overwriteboolean
Whether to overwrite an existing object at the destination pathdefault false
databricksworkspace_cluster_permanent_deletePermanently delete a Databricks cluster by cluster ID.Destructive
Permanently Delete Cluster
Permanently delete a Databricks cluster by cluster ID. Unlike terminating a cluster, this removes it entirely and it can no longer be started or listed. This action is irreversible.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to permanently delete.
databricksworkspace_cluster_terminateTerminate a Databricks cluster by cluster ID.Destructive
Terminate Cluster
Terminate a Databricks cluster by cluster ID. The cluster will be deleted and all its associated resources released.
Inputs
cluster_idstringrequired
The unique identifier of the cluster to terminate.
databricksworkspace_dbfs_deletePermanently delete a file or directory from the Databricks File System (DBFS).Destructive
Delete DBFS File
Permanently delete a file or directory from the Databricks File System (DBFS). This action is irreversible.
- Idempotent
Inputs
pathstringrequired
The DBFS path of the file or directory to delete.
recursiveboolean
Whether to recursively delete a directory and its contentsdefault false
databricksworkspace_job_deleteDelete a Databricks job by job ID.Destructive
Delete Job
Delete a Databricks job by job ID. Active runs are not stopped; the job is removed once its runs finish.
Inputs
job_idintegerrequired
The unique identifier of the job to delete.
databricksworkspace_repo_deletePermanently remove a Git repo from the Databricks workspace.Destructive
Delete Repo
Permanently remove a Git repo from the Databricks workspace. This unlinks the repo and deletes its workspace files; it does not affect the remote Git repository. This action is irreversible.
- Idempotent
Inputs
repo_idstringrequired
The ID of the repo to delete.
databricksworkspace_secret_deleteDelete a secret key from a Databricks secret scope.Destructive
Delete Secret
Delete a secret key from a Databricks secret scope. This action is irreversible.
- Idempotent
Inputs
keystringrequired
The key name of the secret to delete.
scopestringrequired
The name of the secret scope containing the key.
databricksworkspace_workspace_deletePermanently delete a notebook or directory from the Databricks workspace.Destructive
Delete Workspace Object
Permanently delete a notebook or directory from the Databricks workspace. This action is irreversible.
- Idempotent
Inputs
pathstringrequired
The absolute workspace path of the object to delete.
recursiveboolean
Whether to recursively delete a directory and its contentsdefault false

What you can do

Setup

Install the SDK

Set your credentials

Create the Databricks Workspace connection

Tools

Call it

Returns

Get Cluster

Inputs

List Clusters

Inputs

List DBFS Directory

Inputs

Read DBFS File

Inputs

List Columns (INFORMATION_SCHEMA)

Inputs

List Schemas (INFORMATION_SCHEMA)

Inputs

List Table Constraints (INFORMATION_SCHEMA)

Inputs

List Tables (INFORMATION_SCHEMA)

Inputs

Get Job

Inputs

Get Job Run

Inputs

List Job Runs

Inputs

List Jobs

Inputs

Get Object Permissions

Inputs

List Repos

Inputs

Get Current Service Principal

Inputs

List Users

Inputs

List Secrets

Inputs

List Secret Scopes

Inputs

Get SQL Statement Status

Inputs

Get SQL Statement Result Chunk

Inputs

Get SQL Warehouse

Inputs

List SQL Warehouses

Inputs

List Unity Catalogs

Inputs

List Unity Catalog Schemas

Inputs

List Unity Catalog Tables

Inputs

Export Workspace Object

Inputs

Get Workspace Object Status

Inputs

List Workspace Objects

Inputs

Create Cluster

Inputs

Edit Cluster

Inputs

Resize Cluster

Inputs

Restart Cluster

Inputs

Start Cluster

Inputs

Write DBFS File

Inputs

Create Job

Inputs

Trigger Job Run

Inputs