Linksee Memory MCP Server

Local-first agent memory MCP — cross-agent brain with drift detection, 6-layer structured memory + token-saving file diff cache

Local serverstdioGo

What is the Linksee Memory MCP server?

Linksee Memory MCP server exists for a simple reason — assistants are far more useful when they can act on Linksee Memory directly instead of describing what you should do. Local-first agent memory MCP — cross-agent brain with drift detection, 6-layer structured memory + token-saving file diff cache.

What you get

Memory is the entry point. Tie it to a map.yaml of how your product fits together, and the linksee-memory map CLI catches drift with file:line evidence:

What the assistant can call

Once Linksee Memory is connected, these are the calls the assistant has available:

  • rememberSave / update / delete memories. Auto-classifies into 6 layers. Modes: create (default), update (memory_id + fields), delete (forget: true +
  • recallSearch / file history / overview. Modes: search (query), file history (path), entity overview (no params). FTS5 + heat × momentum ranking with
  • read_smartToken-saving file reader with AST diff caching. First read = full content. Re-read unchanged = ~50 tokens. Re-read modified = changed chunks only
  • Uninstall — The Uninstall tool exposed by this server

Setting it up

The server ships on npm as linksee-memory, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Linksee Memory's toolset — remember, recall, read_smart and 1 more — is a fair guide to whether it matches your workflow. It is maintained by michielinksee; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Linksee Memory's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the linksee memory mcp server does with a few real requests.

Available tools

ToolWhat it does
remember**Save / update / delete** memories. Auto-classifies into 6 layers. Modes: create (default), update (memory_id + fields), delete (forget: true + memory_id).
recall**Search / file history / overview.** Modes: search (query), file history (path), entity overview (no params). FTS5 + heat × momentum ranking with match_reasons.
read_smart**Token-saving file reader** with AST diff caching. First read = full content. Re-read unchanged = ~50 tokens. Re-read modified = changed chunks only.
UninstallThe Uninstall tool exposed by this server.

How to install the Linksee Memory MCP server

{
  "mcpServers": {
    "linksee": {
      "command": "npx",
      "args": ["-y", "linksee-memory"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Linksee Memory to remember.
  • Use Linksee Memory to recall.
  • Use Linksee Memory to read smart.

Frequently asked questions

It connects Linksee Memory to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (remember, recall, read_smart, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Linksee Memory directly.