Best MCP Servers for Memory & Knowledge Bases
MCP servers that provide long-term memory, embeddings, and knowledge retrieval.
Memory and knowledge-base MCP servers let agents persist context across conversations. They are the foundation for personal assistants, research agents, and RAG workflows.
Top picks
mem0-lite
Provides self-hosted memory management for coding agents via MCP, with local vector storage and tools for adding, searching, updating, and deleting memories.
T-FLEX CAD 17 MCP
Read-only MCP server providing search and retrieval of T-FLEX CAD 17 API symbols, documentation, and capabilities via a static API layer.
GNB MemoryMCP
A vendor-independent memory layer MCP server that enables multiple LLMs and AI agents to share and persist personal memories, knowledge, and context across sessions, with support for full-text search and tagging.
agent-handoff-memory
An MCP server that gives multiple agents a shared versioned memory with explicit handoff packets, enabling structured context transfer and stale data detection across sessions.
sc-mcp
Connects your Scalable Capital brokerage to any MCP-capable assistant, providing read-only access to portfolio, trades, analytics, quotes, charts, watchlist, and alerts via the official sc CLI.
3gpp-mcp
MCP server that parses 3GPP .docx specifications into structured sections with full-text search, letting LLMs browse, search, and follow cross-references without a vector database.
How to choose
- Prioritize transport: stdio servers run locally; HTTP/remote servers need no install but require network trust.
- Check stars & maintenance: Higher GitHub stars and recent commits usually signal a more reliable project.
- Review security scope: File-system and browser servers can access sensitive data; run them in isolated environments.
- Match your client: Not all MCP clients support every transport; verify compatibility with Claude Desktop, Cursor, or your own agent.
Editorial picks are based on public metadata and keyword matching. They do not constitute endorsements; always review source and license before use.