About Nowledge Mem Mcp Desktop Extension
Nowledge Mem Claude Desktop Extension connects Claude Desktop with a running Nowledge Mem instance. It supports memory search and updates, and can open inline graph views during conversations.
Key features
- 01Search saved memories
- 02Save important context
- 03Update existing knowledge
- 04Open inline graph views
- 05Connect to local or remote Mem
Use cases
- 01Recall saved context during a Claude conversation
- 02Save useful conversation details to Mem
- 03Update existing memory entries
- 04View Mem graphs inline
MCP support
The extension packages an MCP bridge for Claude Desktop and forwards requests to Nowledge Mem, using its local endpoint by default or configured remote access.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMENowledge Mem Claude Desktop Extension
One-click Claude Desktop integration for Nowledge Mem on macOS and Windows, with no separate Python or Node installation required. After installation, Claude can search your memories, save important context, update existing knowledge, and open Mem's inline graph views during any conversation.
Demo Screenshots
https://github.com/user-attachments/assets/a99a1daa-e73c-429e-a17b-0183b2f9671a
For more details, please refer to the Nowledge Mem Documentation.
End User Installation
See also the end user installation details at Nowledge Mem Documentation: Claude Desktop.
- Make sure Nowledge Mem is already running on the same machine, and update Claude Desktop to the latest version.
- Download the Nowledge Mem Claude Desktop extension and double-click the
.mcpbfile to install it. - Restart Claude Desktop once after installation.
Access Mem Anywhere (Remote Access)
By default the extension connects to your local Mem at 127.0.0.1:14242.
For remote access, the extension reads the same shared config file as the nmem CLI:
- macOS / Linux:
~/.nowledge-mem/config.json - Windows:
%USERPROFILE%\\.nowledge-mem\\config.json
If you start Access Anywhere from Nowledge Mem Desktop on the same machine, this file is usually written for you automatically.
If you need to point Claude Desktop at a remote Mem manually, create the file with:
{
"apiUrl": "https://mem.example.com",
"apiKey": "nmem_your_key"
}
Use your server root URL in apiUrl. If you already have an older config ending in /remote-api or /mcp, the extension accepts that too.
Restart Claude Desktop after changing the file.
Troubleshooting
- In Claude Desktop, click the
+button in the chat box and open Connectors to confirm Nowledge Mem appears. - If it does not, open Settings → Extensions → Advanced Settings and inspect the extension status and logs there.
- If you're using Access Anywhere, verify the shared config file above points to the correct URL and key.
Build From Source
The extension uses the Node runtime that ships with Claude Desktop, so end users do not need to install Python or Node.
npm ci
npm test
npm run smoke
npm run pack
For maintainers:
npm run buildbundles the bridge intodist/index.jsnpm testrebuilds and runs the end-to-end MCP forwarding checksnpm run smokevalidates the builtdist/index.jsagainst a mock MCP servernpm run packbuilds, packages, and audits the final.mcpbnpm run verify:packageunpacks the finished bundle and checks the release invariantsnpm cialso installs the pinnedmcpbpacker locally, sonpx @anthropic-ai/mcpb packresolves to the tested version inside this repo- the release archive excludes
node_modules/, source files, and stale Python artifacts
Show Metadata Content
mcp-name: io.github.nowledge-co/server.json
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.