bricks and context
About
Production-grade MCP server for Databricks: SQL Warehouses, Jobs API, multi-workspace support.
Details
- Author
- laraib-sidd
- Categories
- Database, Other, Infrastructure, Automation
Jump to
Setup
Install bricks and context in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/laraib-sidd/bricks-and-context
Follow the installation instructions in the repository README, then restart your MCP client.
Production-grade MCP server for Databricks: SQL Warehouses, Jobs API, multi-workspace support.
Production-grade Model Context Protocol (MCP) server for Databricks
SQL Warehouses · Jobs API · Multi-Workspace · Built for AI Agents
Bricks and Contextlets AI assistants (Cursor, Claude Desktop, etc.) talk directly to your Databricks workspaces through theModel Context Protocol.
Think of it as a bridge: your AI asks questions, this server translates them into Databricks API calls, and returns structured, AI-friendly responses.
git clone https://github.com/laraib-sidd/bricks-and-context.git cd bricks-and-context uv sync # or: pip install -e .
Copy the template and add your credentials:
default_workspace: dev workspaces: - name: dev host: your-dev.cloud.databricks.com token: dapi... http_path: /sql/1.0/warehouses/... - name: prod host: your-prod.cloud.databricks.com token: dapi... http_path: /sql/1.0/warehouses/...
💡auth.yamlis gitignored. Your secrets stay local.
Cursor usesstdio transportand doesn't inherit your shell environment. You need explicit paths.
Step 1: Ensure dependencies are installed
Cmd+Shift+P→"Open MCP Settings"→ Opens~/.cursor/mcp.json
{ "mcpServers": { "databricks": { "command": "uv", "args": [ "--directory", "/path/to/bricks-and-context", "run", "python", "run_mcp_server.py" ], "env": { "MCP_AUTH_PATH": "/path/to/bricks-and-context/auth.yaml", "MCP_CONFIG_PATH": "/path/to/bricks-and-context/config.json" } } } }
{ "mcpServers": { "databricks": { "command": "/path/to/bricks-and-context/.venv/bin/python", "args": ["/path/to/bricks-and-context/run_mcp_server.py"], "env": { "MCP_AUTH_PATH": "/path/to/bricks-and-context/auth.yaml", "MCP_CONFIG_PATH": "/path/to/bricks-and-context/config.json" } } } }
Reload the window to activate the MCP server.
- "List my Databricks jobs"
- "RunSELECT 1on Databricks"
- "Describe the tablecatalog.schema.my_table"
Define multiple workspaces inauth.yaml, then select per-call:
execute_sql_query(sql="SELECT 1", workspace="prod") list_jobs(limit=10, workspace="dev")
Whenworkspaceis omitted, the server usesdefault_workspace.
config.json— Tunable settings (committed)
Any setting can be overridden via environment variable (uppercase, e.g.,MAX_RESULT_ROWS=500).
┌─────────────────────────────────────────────────────────────────┐ │ MCP Client (Cursor / Claude) │ └─────────────────────────────────────────────────────────────────┘ │ stdio ▼ ┌─────────────────────────────────────────────────────────────────┐ │ FastMCP Server │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────────────────┐ │ │ │ SQL Tools │ │ Job Tools │ │ Observability │ │ │ └──────┬──────┘ └──────┬──────┘ └───────────┬─────────────┘ │ └─────────┼────────────────┼─────────────────────┼────────────────┘ │ │ │ ▼ ▼ ▼ ┌──────────────────┐ ┌──────────────────┐ ┌──────────────────────┐ │ Connection Pool │ │ Job Manager │ │ Cache / Perf Monitor │ │ (SQL Connector) │ │ (REST API 2.1) │ │ │ └────────┬─────────┘ └────────┬─────────┘ └──────────────────────┘ │ │ └────────┬───────────┘ ▼ ┌─────────────────────────────────────────────────────────────────┐ │ Databricks Workspace(s) │ │ SQL Warehouse Jobs Service │ └─────────────────────────────────────────────────────────────────┘
uv sync --dev # Install dev dependencies uv run pytest # Run tests uv run black . # Format code uv run mypy src/ # Type check
Official Supabase MCP server for managing Supabase projects, databases, auth, storage, edge functions, and SQL workflows from AI agents.
Visual no-code generator that turns any database into multiple scoped MCP servers — one per access group, with PII masking and fail-closed query scoping built in.
A comprehensive Model Context Protocol (MCP) server for SeaTable that exposes end‑to‑end database capabilities (schema introspection, CRUD, querying, linking, select option management, and file attachment stubs) through 18+ rigorously defined tools.
An MCP server for interacting with Snowflake databases.
Official MCP server for dbt (data build tool) providing integration with dbt Core/Cloud CLI, project metadata discovery, model information, and semantic layer querying capabilities.
Build robust data workflows, integrations, and analytics on a single intuitive platform.
Open source MCP server specializing in easy, fast, and secure tools for Databases.
Query and analyze data with MotherDuck and local DuckDB
Query Streams securely connects MCP clients to live databases through the Query Streams Cloud Network, with no VPNs, inbound ports, or complex setup.
Interact with the SingleStore database platform
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





