Memory MCP
Give AI persistent memory across conversations
How to Install Memory MCP
$npx @modelcontextprotocol/server-memoryRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
About Memory MCP
A simple knowledge-graph memory server. Lets AI remember facts about you and your projects between sessions.
Memory MCP is a AI & LLM MCP server designed for AI engineers, researchers, and product teams. It enables orchestrating models, embeddings, and vector stores from an MCP client by normalising provider APIs into MCP tools for routing and composition. Key capabilities include multi-provider model access, embeddings and similarity search, vector store crud, and structured tool calls that work cleanly inside an LLM context. It integrates with OpenAI, Anthropic, Google, Mistral, Pinecone, Weaviate, Qdrant, and Chroma, and is best suited for AI engineers, researchers, and product teams who need multi-model routing.
Key Features
- memory
- context
- knowledge-graph
- Multi-provider model access
- Embeddings and similarity search
- Vector store CRUD
Pricing
- Core MCP server
- Community support
- Works with any MCP client
- Everything in Free
- Higher usage limits
- Priority support
- Everything in Pro
- SLA & SSO
- Dedicated support
Tier details are indicative — visit the Memory MCP website for current pricing.
Pros & Cons
Pros
- Clean seam between user-facing assistant and AI plumbing
- Swap backends without rewriting prompts
- Surfaces cost and token usage explicitly
Cons
- Adds another moving piece to debug
- Cost can balloon under heavy delegation
- Provider quirks still leak through in edge cases
Best For
- Multi-model routing
- Private knowledge-base queries
- Agent-to-agent delegation
- Cost and latency experiments
Screenshots
Screenshots coming soon —
Submit yours →Our Take on Memory MCP
The reference implementation. Useful for prototyping persistent memory before reaching for a vector store.
Alternatives to Memory MCP
AI image generation inside your Claude workflow
See how Memory MCP compares to EverArt MCP →