About Toon Memory
Toon Memory is an MCP server in the Communication category: offline persistent memory for AI coding agents — 37 tools, 80% fewer calls, no LLM.
Install
Claude Code
claude mcp add toon-memory -- npx -y toon-memorynpx
npx -y toon-memoryThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (35)
context_brief**One-call context briefing**: memory + sessions + health in compact markdown. Use instead of 5-6 separate memory_* calls. Zero LLM, pure deterministic aggregation
Parameters not published.
context_diff**Incremental briefing**: git commits + modified files + new/updated memory + active sessions since last session
Parameters not published.
context_export**Export memory as markdown**: injectable context for system prompts (full or compact)
Parameters not published.
context_focus**Hyper-focused briefing**: only relevant memory + related source files + callers + test files for a query
Parameters not published.
context_generate**Full project briefing**: combines project structure, git state, memory entries, and active sessions in one call. Replaces 5-6 manual tool calls
Parameters not published.
context_health**Memory health audit**: orphan links, duplicates, broken file refs, expired TTL, stale sessions, score 0–100
Parameters not published.
memory_archiveArchive old entries (>30 days) and expired TTL entries
Parameters not published.
memory_backupCreate timestamped backup of memory file (auto-prunes to 10 most recent)
Parameters not published.
memory_capturedList activity auto-captured by hooks (opt-in) or clear the log
Parameters not published.
memory_checkpoint**Session checkpoint**: creates a snapshot of current memory state with 7d TTL. Useful for rollback reference during long sessions
Parameters not published.
Show all 35 tools
memory_compressLLM-powered two-step compression: summarize + overwrite. Uses `anthropic`/`openai` CLI if available, otherwise returns prompt for manual compression
Parameters not published.
memory_consolidate**Cleanup ops**, deterministic (no LLM): `mode: "identical"` (default) dedupes identical-content entries, `"similar"` merges near-duplicates (Jaccard >50%), `"low-quality"` batch-removes low-quality entries (`minQuality`, `dryRun`), `"versions"` retires older library-version entries in favor of the newest
Parameters not published.
memory_decryptDisable encryption
Parameters not published.
memory_diffShow changes since a date (24h, 7d, or exact date)
Parameters not published.
memory_encryptEnable AES-256-GCM encryption
Parameters not published.
memory_export_gistExport memory entries to a GitHub Gist (public or private). Uses `GITHUB_TOKEN` or `gh` CLI
Parameters not published.
memory_export_globalWrite current project memory to the global file (`~/.toon-memory/memory/global.toon`). One-shot share of cross-project conventions
Parameters not published.
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`
Parameters not published.
memory_graph_pathBFS shortest path between two entries in the knowledge graph. Shows how concepts are connected
Parameters not published.
memory_import_gistImport entries from a GitHub Gist. Merges with existing entries (union of tags, max confidence)
Parameters not published.
memory_import_globalMerge cross-project conventions from the global file into this project (one-shot, deterministic, offline). `merge: false` replaces instead
Parameters not published.
memory_merge_sessionsMerge observations across parallel sessions for a file. Deduplicates and optionally auto-promotes to memory
Parameters not published.
memory_pin**Pin an entry with priority 1-5**: pinned entries always appear first in recall results sorted by priority, even without a keyword match
Parameters not published.
memory_primerOne-call context primer: top memories + categories + session file changes. Auto-injected at session start
Parameters not published.
memory_recallSearch memory (use BEFORE reading files, filters expired TTL). `mode: "graph"` expands a relationship-aware subgraph for higher precision. `budget: "tiny"
Parameters not published.
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 quality score and confidence. **Write-path intelligence**: each save is annotated with an evidence level — `verified` when the referenced file exists on disk, `unverified` when it doesn't, `conflict` when it overlaps a warning or critical/high decision (recalled with a boost and surfaced with a ⚠️ CONTRADICTION warning, but never blocks the write)
Parameters not published.
memory_search**Unified search with filters**: same as `memory_recall` plus `category`, `tags`, `from_date`, `to_date` filters. Tag filter uses AND logic — all specified tags must match. `budget` controls output verbosity. `path_scope` filters by glob pattern. `sessionBias` boosts entries from the current git branch
Parameters not published.
memory_secret**Encrypted secrets vault** (`secrets.toon`, AES-256-GCM): `store`/`get`/`list`/`forget`. Keeps `data.toon` readable while sensitive values stay encrypted at rest. Requires `TOON_MEMORY_KEY`
Parameters not published.
memory_sessionsShow active agent sessions (branch, files, last-seen) and soft conflicts for parallel work
Parameters not published.
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
Parameters not published.
memory_statsView memory state (including TTL stats, quality distribution, origin/status breakdown, cold memories below quality/access thresholds, and **hit rate / duplicate / obsolete** metrics)
Parameters not published.
memory_suggestFind related entries for a given context
Parameters not published.
memory_summarySave/retrieve file summaries
Parameters not published.
memory_tag**Batch tag operations**: `add`, `remove`, or `set` tags on one or more entries by key or id
Parameters not published.
memory_unpin**Unpin an entry**: remove the priority flag
Parameters not published.
Ask AI
✦
Ask AI about Toon Memory
Powered by Claude · Grounded in docs
I know everything about Toon Memory. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.