Local-first agent memory MCP — cross-agent brain with drift detection, 6-layer structured memory + token-saving file diff cache
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.
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:
Once Linksee Memory is connected, these are the calls the assistant has available:
remember — Save / update / delete memories. Auto-classifies into 6 layers. Modes: create (default), update (memory_id + fields), delete (forget: true +recall — Search / file history / overview. Modes: search (query), file history (path), entity overview (no params). FTS5 + heat × momentum ranking withread_smart — Token-saving file reader with AST diff caching. First read = full content. Re-read unchanged = ~50 tokens. Re-read modified = changed chunks onlyUninstall — The Uninstall tool exposed by this serverThe 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.
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.
| Tool | What 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. |
| Uninstall | The Uninstall tool exposed by this server. |
{
"mcpServers": {
"linksee": {
"command": "npx",
"args": ["-y", "linksee-memory"]
}
}
}Configuration as documented by the project. Restart the client after saving.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.