Official MCP Memory server
https://github.com/modelcontextprotocol/servers/tree/main/src/memory
Knowledge-graph-based persistent memory MCP server — the canonical reference implementation. npx -y @modelcontextprotocol/server-memory ; configurable via MEMORY_FILE_PATH .
At a glance
- Type
- KG-based persistent memory MCP
- Tier
- T1
- Section
- Claude Code memory mechanisms
- Created
- 2024-11
- Latest release
- 2026.1.26 2026-01-27
- License
- Custom
- GitHub
- 85.1k★ +4.8k/mo TypeScript
- Pricing
- free / open source (MIT)
- Funding
- not applicable — not commercial
Taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- cross-session
- update
- overwrite
- unit
- fact
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: Claude-Code-native + MCP-portable memory
Anti-fit: not for non-Claude-Code clients (some are MCP-portable)
Pros & cons
Pros
Reference implementation in the MCP spec; smallest possible memory primitive — useful for testing and lightweight cases.
Cons
Minimal feature set — no extraction, no governance, no retention policy; production deployments quickly outgrow it.
Claims & capabilities
Knowledge-graph-based persistent memory MCP server — the canonical reference implementation; npx -y @modelcontextprotocol/server-memory; configurable via MEMORY_FILE_PATH; release 2026.1.26 (2026-01-27); 85.1k★ on parent modelcontextprotocol/servers; +4.8k/mo
Technical surface
- API surface
- MCP (stdio); knowledge-graph tools (create_entities/relations/observations, read/search/delete)
- Backend storage
- file (JSON)
- Deployment
- local (Node.js MCP server; local JSON file)
- Embedding model
- not applicable — knowledge graph store
- Multi-tenancy
- not applicable — local
- MCP
- native (first-party) — reference implementation
- A2A
- not supported
- OpenTelemetry
- no
Compare Official MCP Memory server with…
Similar systems
Other claude code memory mechanisms in the catalog, ranked by inbound references.
- Anthropic Auto Dream T1
Background sub-agent in Claude Code that periodically scans ~/.claude/projects/<project>/memory/ + recent JSONL transcripts via grep, prunes stale notes, deduplicates, resolves contradictions, converts relative dates to absolute timestamps, and rewrites MEMORY.md (kept under 200 lines). Triggers automatically when 24+ hours elapsed AND 5+ sessions completed; manually via /dream.
- Claude Code auto-memory T1
Persistent file-based memory at ~/.claude/projects/<project>/memory/ with a MEMORY.md index plus typed memory files (user / feedback / project / reference). Loaded into context across sessions.
- claude-brain T2
Claude Code plugin packaging of Memvid (see Dedicated memory layers). Wraps the Memvid .mv2 single-file store as a slash-command-installable plugin so per-project memory becomes a git-committable file inside the repo.
- Claude-CursorMemoryMCP T2
FastAPI server. RBAC + API-key auth, encryption, backup/recovery, embedding pipeline with deduplication. Only server in this list with role-based access control over pgvector.
- claude-mem T1
Hooks into Claude Code's session lifecycle; compresses tool outputs into ~500-token observations via Claude's agent SDK. SQLite + FTS5 with optional Chroma vector. "Endless Mode" compresses in-flight to extend session length. Captures what the agent did , not just what the user typed.
- claude-supermemory T2
Wraps Supermemory cloud API. Team memory shared across project members, separate from personal memories. Auto-capture on session end; per-repo config.
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: requires Claude Code or MCP client; BYO storage
- Model Context Protocol (MCP spec) depends on at runtime — adjacent-infrastructure cell: requires Claude Code or MCP client; BYO storage
Referenced by (2)
- Continue.dev Memory MCP builds on — Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP
- mcp-knowledge-graph forks — KG-based local fork of @modelcontextprotocol/server-memory