Databricks Docs MCP Server
Enables semantic search over Databricks docs, API reference, Terraform provider docs, and knowledge base via tools like search_databricks_docs and research.
README
Databricks Docs MCP Server
Semantic search over Databricks documentation, API reference, Terraform provider docs, and knowledge base — as an MCP server for Claude Code.
Uses all-mpnet-base-v2 embeddings + ChromaDB with keyword boosting for high-relevance results.
Setup
cd tools/databricks-docs-mcp
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Build the Index
python indexer.py
Clones doc repos, scrapes docs.databricks.com + kb.databricks.com, chunks, embeds, and stores in chroma_data/. Takes ~15 min on first run (uses MPS GPU on Apple Silicon). Skips already-indexed collections on re-run.
Connect to Claude Code
Add to .mcp.json:
{
"mcpServers": {
"databricks-docs": {
"command": "/path/to/tools/databricks-docs-mcp/.venv/bin/python",
"args": ["/path/to/tools/databricks-docs-mcp/server.py"]
}
}
}
Run /mcp in Claude Code to connect.
Tools
| Tool | What it searches |
|---|---|
search_databricks_docs |
General docs — Genie, Unity Catalog, warehouses, etc. |
search_databricks_api |
REST API & Python SDK reference |
search_terraform_databricks |
Terraform provider resources |
search_databricks_genai |
GenAI Cookbook — RAG, evaluation, chunking |
search_databricks_cli |
CLI commands, bundles, workspace ops |
search_databricks_kb |
Troubleshooting & known issues |
search_all |
All collections at once |
research |
Deep multi-query research on a topic |
list_collections |
Show collections and chunk counts |
list_pages |
List indexed pages in a collection |
fetch_page |
Get all chunks for a specific page |
Doc Sources
| Source | Collection | ~Chunks |
|---|---|---|
| docs.databricks.com | databricks_docs |
14,200 |
| kb.databricks.com | databricks_kb |
1,100 |
| terraform-provider-databricks | terraform_databricks |
2,200 |
| databricks-sdk-py | databricks_api |
107 |
| genai-cookbook | databricks_genai |
176 |
| databricks CLI | databricks_cli |
689 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.