Toon Memory MCP Server

Offline persistent memory for AI coding agents — 37 tools, 80% fewer calls, no LLM

Local serverstdioTypeScript

What is the Toon Memory MCP server?

If you already use Toon Memory, the toon memory mcp server is the piece that lets your assistant work with it directly. Offline persistent memory for AI coding agents — 37 tools, 80% fewer calls, no LLM.

What the server does

Ever had that feeling where your AI agent forgets everything from yesterday's session? You explain the same architecture decision for the third time, and it still suggests the approach you already rejected?

  • MCP Resources — — Read memory as context without tool invocations, including a System Primer (auto-generated knowledge map)
  • 15 agents supported — — OpenCode, VS Code, Claude Code, Cursor, Windsurf, Cline, Continue, Codex CLI, Gemini CLI, Zed, Antigravity, Aider, KiloCode, OpenClaw, Kiro
  • Interactive installer — — Select which agents to configure from a menu
  • SessionStart hooks — — Auto-reminders for Claude Code, Codex CLI, Gemini CLI, Antigravity
  • TOON format — — 22% fewer tokens than JSON (measured), better LLM comprehension
  • Per-project memory — — Each project gets its own memory file

Installation

toon-memory on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Available tools

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

  • memory_remember — Save a decision, pattern, bug, knowledge, or warning (negative "do NOT do this" memory, recalled with a boost) — optional TTL, auto-tag
  • memory_recall — Search memory (use BEFORE reading files, filters expired TTL). mode: "graph" expands a relationship-aware subgraph for higher precision. budget
  • memory_smart_recallUnified recall: BM25 + graph + decay + quality in one call. sessionBias boosts entries from the current git branch. explain: true appends
  • memory_forgetLifecycle ops by key or id: action: "soft" (default) marks obsolete, "hard" permanently removes, "restore" brings back to active, "supersede"
  • memory_stats — View memory state (including TTL stats, quality distribution, origin/status breakdown, cold memories below quality/access thresholds, and **hit rate
  • memory_summary — Save/retrieve file summaries
  • memory_archive — Archive old entries (>30 days) and expired TTL entries
  • memory_diff — Show changes since a date (24h, 7d, or exact date)
  • memory_suggest — Find related entries for a given context
  • memory_encrypt — Enable AES-256-GCM encryption
  • memory_decrypt — Disable encryption
  • memory_backup — Create timestamped backup of memory file (auto-prunes to 10 most recent)

Credentials and setup notes

Configuration is passed through the environment: GITHUB_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

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 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Toon Memory.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Toon Memory's toolset — memory_remember, memory_recall, memory_smart_recall and 11 more — is a fair guide to whether it matches your workflow. It is maintained by LuiggiVal08; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
memory_rememberSave a decision, pattern, bug, knowledge, or **warning** (negative "do NOT do this" memory, recalled with a boost) — optional TTL, auto-tag inference, links to build the memory graph, merge-dedup on same key, auto qualit
memory_recallSearch memory (use BEFORE reading files, filters expired TTL). mode: "graph" expands a relationship-aware subgraph for higher precision. budget: "tiny"
memory_smart_recall**Unified recall**: BM25 + graph + decay + quality in one call. sessionBias boosts entries from the current git branch. explain: true appends per-entry reasons, budget_tokens caps output by estimated tokens. Use at the S
memory_forget**Lifecycle ops** by key or id: action: "soft" (default) marks obsolete, "hard" permanently removes, "restore" brings back to active, "supersede" retires it with a superseded_by link to new_key
memory_statsView memory state (including TTL stats, quality distribution, origin/status breakdown, cold memories below quality/access thresholds, and **hit rate / duplicate / obsolete** metrics)
memory_summarySave/retrieve file summaries
memory_archiveArchive old entries (>30 days) and expired TTL entries
memory_diffShow changes since a date (24h, 7d, or exact date)
memory_suggestFind related entries for a given context
memory_encryptEnable AES-256-GCM encryption
memory_decryptDisable encryption
memory_backupCreate timestamped backup of memory file (auto-prunes to 10 most recent)
memory_capturedList activity auto-captured by hooks (opt-in) or clear the log
memory_checkpoint**Session checkpoint**: creates a snapshot of current memory state with 7d TTL. Useful for rollback reference during long sessions

How to install the Toon Memory MCP server

{
  "mcpServers": {
    "toon-memory": {
      "command": "npx",
      "args": ["-y", "toon-memory"],
      "env": {
        "GITHUB_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GITHUB_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Toon Memory to memory remember.
  • Use Toon Memory to memory recall.
  • Use Toon Memory to memory smart recall.

Frequently asked questions

It connects Toon Memory to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (memory_remember, memory_recall, memory_smart_recall, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Toon Memory directly.