MCP AutoMem
This connects your AI assistant to AutoMem's graph-vector memory backend, giving it persistent recall across all your conversations in Claude Desktop, Cursor, and other MCP clients. It exposes tools to store memories, query by semantic similarity, and create 11 different relationship types between memories (like "causes," "supports," "contradicts"). The architecture combines FalkorDB's graph database with Qdrant's vector search for sub-second retrieval. Setup takes 30 seconds if you're running AutoMem locally or on Railway. You get a one-click installer for Claude Desktop, automatic memory rules for Cursor, and session hooks for Claude Code. Reach for this when you want your AI to remember your coding patterns, past decisions, and project context instead of starting every conversation from scratch.
- GitHub stars
- 51
- tools
- 6
- auth
- Secret needed
- transport
- STDIO, HTTP, SSE
- last updated
- Jan 7, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
store_memorySave memories with content, tags, importance, metadata, in single or batch mode.
Save memories with content, tags, importance, metadata, in single or batch mode.
No parameter schema in public metadata yet.
recall_memoryFetch a memory by ID, list memories by tag, or perform ranked hybrid retrieval over stored memories.
Fetch a memory by ID, list memories by tag, or perform ranked hybrid retrieval over stored memories.
No parameter schema in public metadata yet.
associate_memoriesCreate relationships between memories, as a single pair or in batch.
Create relationships between memories, as a single pair or in batch.
No parameter schema in public metadata yet.
update_memoryModify existing memories.
Modify existing memories.
No parameter schema in public metadata yet.
delete_memoryRemove one memory by ID, or bulk-delete memories matching any of the given tags.
Remove one memory by ID, or bulk-delete memories matching any of the given tags.
No parameter schema in public metadata yet.
check_database_healthMonitor service health, degraded state, sync counts, vector dimensions, and enrichment diagnostics.
Monitor service health, degraded state, sync counts, vector dimensions, and enrichment diagnostics.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
AutoMem MCP: Give Your AI Perfect Memory
AutoMem
One command. Infinite memory. Perfect recall across all your AI tools.
npx @verygoodplugins/mcp-automem@latest install
Your AI assistant now remembers everything. Forever. Across every conversation.
Details
- Repository
- github.com/verygoodplugins/mcp-automem
- Website
- automem.ai/?utm_source=mcp-registry
- Category
- AI & LLM Tools
- Package
@verygoodplugins/mcp-automem- Transport
- STDIO, HTTP, SSE
- Auth
- Required
- Registry
- MCP registry, active
More from verygoodplugins
Related AI & LLM Tools MCP servers
View all
Engramtstockham96/engramIntelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.39stars
Local FAISS MCP Servernonatofabio/local_faiss_mcpLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.30stars
SAME - Stateless Agent Memory Enginesgx-labs/statelessagentPersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.19stars
Promptheusabhichandra21/promptheusAI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)17stars
MCP Imagenatemimo-3/mcp-imagenateMCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)15stars
Cludesebbsssss/cludePortable agent memory anchored on Solana. Local SQLite + vector recall, open export.15stars