Skip to main content
Glama
samhavens

Databricks MCP Server

by samhavens
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

Related Servers

Alternatives to Databricks MCP Server

No user-submitted related servers found.

    Related Servers

    • Databricks MCP Server

      JustTryAI
      A
      license
      B
      quality
      D
      maintenance
      A server that implements the Model Completion Protocol (MCP) to allow LLMs to interact with Databricks resources including clusters, jobs, notebooks, and SQL execution through natural language.
      11
      48
      MIT

    • Databricks MCP Server

      mikephelankk-hub
      F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants like Claude to interact with Databricks workspaces through a secure MCP server running on Databricks Apps. Supports custom prompts and tools using the Databricks SDK.
      -

    • databricks_ops_mcp

      Sameet1308
      F
      license
      Not graded
      quality
      C
      maintenance
      A governed MCP server exposing Databricks operations as tools for jobs orchestration, SQL execution, notebook creation, Unity Catalog governance, lineage, clusters, and DLT pipelines, with safety features like dry-run and audit logging.
      -

    • Databricks MCP Server Template

      db-mattmolony
      -
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI assistants like Claude to interact with Databricks workspaces through secure OAuth authentication. Supports custom prompts, tools for workspace management, and SQL query execution via a deployable MCP server on Databricks Apps.
      -

    • databricks-mcp

      ChrisChoTW
      A
      license
      C
      quality
      D
      maintenance
      A read-only MCP server that enables users to query Databricks SQL, browse metadata, and monitor Delta Lake tables. It also supports tracking Databricks Jobs, DLT Pipelines, and cluster metrics through natural language interfaces.
      25
      4
      MIT
    Deploy Server
    RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

    TDQS

    B3.3/5.0

    Scored across 19 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific Databricks resources and actions. There is no ambiguity: create_* tools create resources, list_* tools list resources, execute_sql vs execute_sql_nonblocking handle different execution modes, and upload_file_to_dbfs vs upload_file_to_volume target different storage systems. The descriptions reinforce these distinctions.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case throughout. Verbs like create, list, get, execute, run, start, terminate, export, and upload are used predictably with appropriate nouns (cluster, job, notebook, sql, files, etc.). There are no deviations in naming conventions.

    Tool Count4/5

    With 19 tools, the count is slightly high but reasonable for a comprehensive Databricks interface covering clusters, jobs, notebooks, SQL execution, and file management. It includes core operations for each domain without being excessive, though some tools like list_job_runs and list_jobs could potentially be consolidated to reduce count.

    Completeness5/5

    The tool surface provides complete CRUD/lifecycle coverage for Databricks domains: clusters (create/get/list/start/terminate), jobs (create/list/run with detailed run tracking), notebooks (create/list/export), SQL execution (blocking/non-blocking with status check), and file management (list/upload for both DBFS and Unity Catalog volumes). There are no obvious gaps that would cause agent failures.

    Maintenance

    ActivityInactive
    ResponsivenessNo issues

    Resources