Memory & Vector Stores MCP servers
MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in this category.
MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in this category.
Provides AI agents with a persistent memory layer and virtual filesystem to read, search, and update project context.
$claude mcp add mcp-server -- npx -y @memofs/mcp-serverEnables multiple AI applications to share a single local memory for recalling, remembering, and forgetting information on macOS.
$claude mcp add dawnmere-connector -- npx -y dawnmere-connectorProvides AI agents with persistent, local semantic long-term memory using SQLite and local transformer embeddings without cloud dependencies.
$claude mcp add longtermmemory-mcp -- npx -y longterm-memory-mcpProvides a local-first persistent SQLite key/value store that allows AI agents to share context and memory across different sessions and tools.
$claude mcp add delx-memory -- npx -y delx-memoryTurns your Obsidian vault into a private, searchable memory for AI clients like Claude and Cursor using hybrid retrieval.
$claude mcp add brain-mcp -- npx -y debawho-brain-mcpEnables AI agents to perform hybrid search, deterministic record lookups, and citation-grounded RAG over isolated, multi-tenant data stores.
$claude mcp add vectros-mcp-server -- npx -y @vectros-ai/mcp-serverEnables AI applications to share a single unified memory for recalling, remembering, and forgetting information across different clients.
$claude mcp add dawnmere-connector -- npx -y dawnmere-connectorTurns a large codebase into a searchable hierarchical feature graph an AI client can navigate, analyze, and edit safely.
Gives AI agents a shared local .wax memory file to remember, recall, and search text, photos, and video across sessions.
Provides persistent agent memory and a self-building knowledge graph to reduce context token usage by up to 90%.
Lets an AI client store, chunk, and semantically search local documentation across a built-in web dashboard and REST API.
$claude mcp add mcp-documentation-server -- npx -y @andrea9293/mcp-documentation-serverLets an AI client semantically search local files and code, returning matching source text, and warm up search indexes.
$claude mcp add vexor -- uvx vexorGives AI agents semantic, episodic, and procedural memory that persists across sessions and learns from failed workflows.
$claude mcp add --transport http mengram https://mengram.io/mcpProvides a cognitive memory engine for AI agents that consolidates duplicates, detects contradictions, and manages memory decay.
Provides an offline agentic memory system using a fused vector, graph, and columnar engine to remember, recall, and relate information.
$https://github.com/cyberlife-coder/VelesDB/releases/download/velesdb-memory-v0.17.1/velesdb-memory-0.17.1-aarch64-apple-darwin.mcpbGives an AI client self-learning vector memory to store patterns, search them semantically, and improve ranking from feedback.
$claude mcp add agentdb -- npx -y agentdbProvides a Git-backed permanent memory for AI agents to share durable, human-readable Markdown memories across different clients.
$claude mcp add perenna -- uvx perennaGives AI assistants a local, human-like memory system where memories decay over time and strengthen with repeated use.
Provides persistent, local-first searchable memory for AI agents using hybrid vector and keyword retrieval.
$claude mcp add memo -- uvx mlx-memoProvides fully local, air-gapped semantic memory for AI agents with deterministic storage and point-in-time fact retrieval.
$claude mcp add genome -- uvx genome-memory