Databricks Docs MCP Server
Searches Databricks documentation, API reference, and knowledge base for topics like Unity Catalog, Genie, SQL warehouses, CLI commands, and troubleshooting.
Searches Databricks Terraform provider documentation for resources and data sources.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Databricks Docs MCP ServerSearch how to set up Unity Catalog external location"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.txtRelated MCP server: Marcus Local MCP Server
Build the Index
python indexer.pyClones 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 |
| General docs — Genie, Unity Catalog, warehouses, etc. |
| REST API & Python SDK reference |
| Terraform provider resources |
| GenAI Cookbook — RAG, evaluation, chunking |
| CLI commands, bundles, workspace ops |
| Troubleshooting & known issues |
| All collections at once |
| Deep multi-query research on a topic |
| Show collections and chunk counts |
| List indexed pages in a collection |
| Get all chunks for a specific page |
Doc Sources
Source | Collection | ~Chunks |
docs.databricks.com |
| 14,200 |
kb.databricks.com |
| 1,100 |
terraform-provider-databricks |
| 2,200 |
databricks-sdk-py |
| 107 |
genai-cookbook |
| 176 |
databricks CLI |
| 689 |
This server cannot be deployed
Maintenance
Related MCP Connectors
Ingest, manage, and retrieve documents for RAG-powered AI applications
Versioned documentation registry and semantic search for AI tools and coding assistants.
Search your knowledge bases from any AI assistant using hybrid RAG.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables semantic search across documents and code repositories using RAG (Retrieval-Augmented Generation) with vector embeddings. Automatically indexes PDF documents and performs relevance-scored lookups through ChromaDB and sentence transformers.-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to semantically search through indexed documentation websites and local code repositories using OpenAI embeddings and ChromaDB vector storage.-
- FlicenseAqualityDmaintenanceEnables semantic search across multiple AI library documentations to keep coding assistants up-to-date.11-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.2MIT