Lorekeeper MCP Server

Self-improving MCP memory server for AI agents. One command, no cloud, no config.

Local serverstdioGo

What is the Lorekeeper MCP server?

Connect Lorekeeper to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Self-improving MCP memory server for AI agents. One command, no cloud, no config. The lorekeeper mcp server is what makes that connection.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • lore_search — Hybrid semantic + keyword search with relevance scores
  • lore_remember — Fast one-shot memory save (auto-titles, auto-links)
  • lore_insert — Bulk structured insert with custom scores and links
  • lore_update — Feedback loop — rate memories, drive quality
  • lore_forget — Soft-delete wrong or outdated memories
  • lore_reflect — End-of-session: extract learnings, auto-save discoveries
  • lore_processed_sessions — Check which sessions are already processed
  • lore_recommend_links — Suggest candidate links between related memories
  • lore_get_suggestions — List pending link suggestions from the sweep engine
  • lore_review_suggestion — Accept or reject one or more link suggestions (batch)

Installation

Installation goes through your MCP client rather than a global install: point it at agentmemory on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

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. Lorekeeper's toolset — lore_search, lore_remember, lore_insert and 7 more — is a fair guide to whether it matches your workflow.

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

Worth knowing first

  • 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.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Lorekeeper.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
lore_searchHybrid semantic + keyword search with relevance scores
lore_rememberFast one-shot memory save (auto-titles, auto-links)
lore_insertBulk structured insert with custom scores and links
lore_updateFeedback loop — rate memories, drive quality
lore_forgetSoft-delete wrong or outdated memories
lore_reflectEnd-of-session: extract learnings, auto-save discoveries
lore_processed_sessionsCheck which sessions are already processed
lore_recommend_linksSuggest candidate links between related memories
lore_get_suggestionsList pending link suggestions from the sweep engine
lore_review_suggestionAccept or reject one or more link suggestions (batch)

How to install the Lorekeeper MCP server

{
  "mcpServers": {
    "lorekeeper": {
      "command": "npx",
      "args": ["-y", "agentmemory"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Lorekeeper to lore search.
  • Use Lorekeeper to lore remember.
  • Use Lorekeeper to lore insert.

Frequently asked questions

It connects Lorekeeper to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (lore_search, lore_remember, lore_insert, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Lorekeeper directly.