Mem0 MCP
Give AI agents persistent long-term memory that improves with every interaction
BestMCPTools
Mem0 MCP
bestmcptools.org
Maintenance status
ActiveThe linked repository is the main Mem0 project; the MCP server is a companion package.
How to Install Mem0 MCP
$npx -y @mem0ai/mem0-mcpCompatible with: All Models.
Setup by client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"mem0-mcp": {
"command": "npx",
"args": [
"-y",
"@mem0ai/mem0-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"mem0-mcp": {
"command": "npx",
"args": [
"-y",
"@mem0ai/mem0-mcp"
]
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"mem0-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mem0ai/mem0-mcp"
]
}
}
}Claude Code (terminal)
claude mcp add mem0-mcp -- npx -y @mem0ai/mem0-mcpAdd any API keys or environment variables the server's README lists.
About Mem0 MCP
Mem0 is an AI memory layer that stores, retrieves, and updates user-specific context across sessions. Its MCP server lets any AI agent save important facts, preferences, and past conversation context to a persistent memory store, then recall them intelligently in future sessions. This solves the fundamental limitation of stateless LLMs (every session starts fresh) by giving agents access to a growing knowledge base of what it knows about the user, their projects, and their preferences. Supports hybrid vector + graph memory for both semantic and relational recall.
Mem0 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
- long-term-memory
- personalization
- ai-agents
- vector-search
Pricing
Freemium: from Free
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
Our Take on Mem0 MCP
The memory layer every persistent AI agent needs: fills the gap that raw LLMs fundamentally cannot.