Databricks MCP Servers vs Memory (Knowledge Graph)

A side-by-side comparison of two AI, Data & Knowledge servers — tools, transport, auth, maintenance, and copy-paste config for each.

	Databricks MCP Servers Databricks Labs server exposing Unity Catalog functions, vector search indexes and Genie spaces as agent tools. Unverified stdio (local) OAuth Stale Python	Memory (Knowledge Graph) Official MCP server providing persistent, file-backed knowledge-graph memory across sessions. Verified stdio (local) No auth TypeScript
Category	AI, Data & Knowledge	AI, Data & Knowledge
Language	Python	TypeScript
Transport	stdio (local)	stdio (local)
Auth	OAuth	None
GitHub stars	93	74k
Last commit	11 months ago	5 months ago
Verified
Actively maintained
Install	`git clone https://github.com/databrickslabs/mcp && uv --directory ./mcp run unitycatalog-mcp -s your_catalog.your_schema`	`npx -y @modelcontextprotocol/server-memory`
Repo	Open	Open

Verdict

Pick Databricks MCP Servers if you prefer its approach (databricks labs server exposing unity catalog functions, vector search indexes and genie spaces as agent tools).

Pick Memory (Knowledge Graph) if you prefer the more popular, battle-tested option, and you want zero-setup with no API key.

Add Databricks MCP Servers

Install / run

git clone https://github.com/databrickslabs/mcp && uv --directory ./mcp run unitycatalog-mcp -s your_catalog.your_schema

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "databricks-mcp-servers": {
      "command": "/path/to/uv/executable/uv",
      "args": [
        "--directory",
        "/path/to/this/repo",
        "run",
        "unitycatalog-mcp",
        "-s",
        "your_catalog.your_schema",
        "-g",
        "genie_space_id_1,genie_space_id_2"
      ]
    }
  }
}

Add Memory (Knowledge Graph)

Install / run

npx -y @modelcontextprotocol/server-memory

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memory-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ],
      "env": {
        "MEMORY_FILE_PATH": "/absolute/path/to/memory.jsonl"
      }
    }
  }
}

FAQ

Databricks MCP Servers or Memory (Knowledge Graph) — which is better?

Pick Databricks MCP Servers if you prefer its approach (databricks labs server exposing unity catalog functions, vector search indexes and genie spaces as agent tools). Pick Memory (Knowledge Graph) if you prefer the more popular, battle-tested option, and you want zero-setup with no API key.

Can I use both Databricks MCP Servers and Memory (Knowledge Graph)?

Yes — MCP clients let you enable multiple servers at once. Add both configs to your client's mcpServers and use whichever tool fits the task.

Do Databricks MCP Servers and Memory (Knowledge Graph) work with Claude, Cursor and Windsurf?

Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.

View Databricks MCP Servers →View Memory (Knowledge Graph) →More comparisons →