In-depth architectural comparison of the Claude Memory Manager and Toon Memory MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Claude Memory Manager
Knowledge & Memory · Local stdio
Quality: 48/100 (Fair) | Auth: No auth required
Toon Memory
Knowledge & Memory · Local stdio
Quality: 57/100 (Good) | Auth: No auth required
Verdict Summary: Choose Claude Memory Manager if you need specialized Knowledge & Memory tools running via a local process. Choose Toon Memory if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Claude Memory Manager when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Save 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 quality score and confidence. **Write-path intelligence**: each save is annotated w…
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Claude Memory Manager is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Toon Memory belongs to Knowledge & Memory using local stdio subprocess. Select Claude Memory Manager when you need capabilities focused on knowledge & memory and Toon Memory when you require tools for knowledge & memory.
Search 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 START of every task. Returns compact, token-efficient output
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