Databricks is a data analytics platform that provides data lakehouse solutions for businesses, combining data warehouses and data lakes to offer unified analytics for data engineering, machine learning, and business intelligence.
Agentic data quality MCP server — runs structured validation rules against warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres), diagnoses failures with LLM root cause analysis, and proposes SQL remediations. Full audit trail of every AI decision.
Last updated
6
3
Apache 2.0
Why this server?
Manages tag-based data masking, access governance, and classification for Databricks databases through the ALTR platform.
Enables AI assistants to manage data security on the ALTR platform for Snowflake, Databricks, and OLTP databases, offering 99 tools across 10 domains including tag masking, policies, classification, and access governance.
Last updated
100
GPL 3.0
Why this server?
Provides access to Databricks functionality through tools that allow interacting with clusters (listing, creating, terminating, starting), jobs (listing, running), notebooks (listing, exporting), files (browsing DBFS paths), and executing SQL queries on a Databricks instance.
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.
Last updated
11
48
MIT
Why this server?
Supports per-user authentication and service orchestration for Databricks via External OAuth within the pAIchart service mesh.
AI-native service orchestration platform. Discover MCP services by capability, chain multi-service-workflows at runtime, and authenticate per-user via JWKS/External OAuth. A single pAIchart MCP server needs only 10 tools to access hundreds of registered local or network MCP servers solving the context issue individual MCP server tools impose. Enabled by pAIchart's service_call innovation.
Last updated
2
MIT
Why this server?
Allows querying Databricks via Unity Catalog or Hive metastore.
Query SQL databases (SQLite, PostgreSQL, BigQuery, Databricks) in natural language through a business semantic layer — glossary, metrics, and a data dictionary grounded against your real schema. Read-only by default, with an embedded SQLite + sqlite-vec metadata store and no external infra required.
Last updated
25
1
MIT
Why this server?
Allows connection to Databricks-hosted MLflow tracking servers using Databricks PAT or service-principal tokens, enabling management of experiments, runs, models, and traces on Databricks.
Local MCP server for AI Model Manager that captures SQL data-model metadata and exposes it to MCP clients over stdio.
Last updated
2
MIT
Why this server?
Provides access to Databricks functionality including cluster management, job management, notebook operations, file system operations (DBFS and Unity Catalog volumes), and SQL execution capabilities.
A fixed Model Completion Protocol (MCP) server that enables LLMs like Claude Code to interact with Databricks functionality including clusters, jobs, notebooks, and SQL execution through natural language commands.
Last updated
19
4
MIT
Why this server?
Performs security scanning of Databricks environments to detect misconfigurations and dependency vulnerabilities.
AI supply chain security scanner for MCP servers and AI agents. 18 tools for CVE scanning, blast radius mapping, CIS benchmarks, SBOM generation, and compliance enforcement across OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, and EU AI Act.
