A side-by-side look at the Agent Memory and Deja Vu MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Memory for knowledge & memory work as a local process; choose Deja Vu for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agent Memory when
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer a local stdio subprocess transport.
Its auth model fits you: No auth required.
You want tools like memory.fetch_context, memory.propose_update, memory.status.
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agent Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. Deja Vu belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Agent Memory for knowledge & memory work and Deja Vu for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Agent Memory is listed as free. Auth: no auth required. Deja Vu is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add xchucx-agent-memory and vshulcz-deja-vu as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Memory has a quality signal of 60/100 (Good) with 4 views, 0 installs and 12 GitHub stars. Deja Vu has 69/100 (Great) with 2 views, 0 installs and 1,209 GitHub stars.