JupyterMCP 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.
| JupyterMCP Connect Claude to Jupyter Notebook 6.x to insert, execute, edit and manage cells via MCP. Unverified stdio (local) No auth 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 | None | None |
| GitHub stars | 129 | 74k |
| Last commit | 1 year ago | 5 months ago |
| Verified | ||
| Actively maintained | ||
| Install | git clone https://github.com/jjsantos01/jupyter-notebook-mcp.git | npx -y @modelcontextprotocol/server-memory |
| Repo | Open | Open |
Verdict
Pick JupyterMCP if you prefer its approach (connect claude to jupyter notebook 6.x to insert, execute, edit and manage cells via mcp).
Pick Memory (Knowledge Graph) if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Add JupyterMCP
git clone https://github.com/jjsantos01/jupyter-notebook-mcp.gitPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"jupytermcp": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/REPO/FOLDER/src",
"run",
"jupyter_mcp_server.py"
]
}
}
}Add Memory (Knowledge Graph)
npx -y @modelcontextprotocol/server-memoryPaste 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
JupyterMCP or Memory (Knowledge Graph) — which is better?
Pick JupyterMCP if you prefer its approach (connect claude to jupyter notebook 6.x to insert, execute, edit and manage cells via mcp). Pick Memory (Knowledge Graph) if you want the official, vendor-maintained server, and you prefer the more popular, battle-tested option.
Can I use both JupyterMCP 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 JupyterMCP and Memory (Knowledge Graph) work with Claude, Cursor and Windsurf?
Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.