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 local long-term memory for AI assistants using hybrid search, a knowledge graph, and an encrypted vault.
$claude mcp add mgi-mind -- npx -y mgi-mindProvides a local-first persistent memory and knowledge graph for AI coding agents to store decisions, patterns, and indexed documentation.
$claude mcp add turbo-quant-memory -- uvx turbo-quant-memoryProvides a token-light local memory layer for AI agents using SQLite with hybrid BM25 and dense retrieval.
$claude mcp add tinycontext -- docker run -i --rm docker.io/marcellm01/tinycontext:v0.5.4Provides persistent memory for Claude Code by automatically saving and retrieving conversation context, decisions, and preferences across sessions.
$claude mcp add memory-mcp -- uvx chenxiaofie-memory-mcpProvides persistent, evidence-backed memory for AI agents by linking claims to their original source events and review history.
$claude mcp add provena -- uvx provena-agent-memoryProvides an MCP interface to an existing Open Agent Memory deployment for cited memory recall and durable information retention.
$claude mcp add oam -- npx -y @rocke-dong/oam-mcpProvides persistent semantic memory for AI agents with automatic context management and write-back capabilities to Slack, Gmail, and GitHub.
$claude mcp add ainative-zerodb-memory-mcp -- npx -y ainative-zerodb-memory-mcpProvides AI agents with structured, persistent memory to store evolving understanding, rationale, and multi-agent coordination through a shared graph.
$claude mcp add understanding-graph -- npx -y understanding-graphProvides persistent, scoped memory for AI agents through four explicit stdio tools for searching, adding, updating, and deleting memories.
$claude mcp add qdrant-memory-mcp -- uvx qdrant-memory-mcpProvides AI agents with repository-aware memory and context retrieval through semantic search and codebase ingestion.
$claude mcp add cuemap-mcp -- npx -y cuemap-mcpProvides hosted memory for AI agents with provenance, contradiction surfacing, and snapshot rollback capabilities.
$claude mcp add bilinc -- uvx bilincProvides inspectable, correction-aware semantic memory for AI agents through a CLI, TypeScript SDK, and MCP server.
Lets AI coding assistants run semantic code search, symbol graph navigation, and persistent memory queries over an indexed codebase.
Provides automatic local memory capture and recall for AI agents using a single SQLite file to maintain long-term context across sessions.
Gives AI agents persistent local memory with semantic recall, structured facts, and cross-agent context sharing.
Gives AI clients persistent cross-session memory stored locally, with encrypted sync and 30 MCP tools for storing and retrieving context.
$claude mcp add cortex -- docker run -i --rm ghcr.io/gambletan/cortex:v1.8.0Provides persistent, workspace-isolated codebase memory for IDEs using local vector indexing and tree-sitter parsing.
Provides a self-evolving Zettelkasten-style memory graph that allows AI agents to store, link, and evolve knowledge through semantic and structural search.
$claude mcp add a-mem-mcp -- uvx a-memProvides project-scoped memory for AI clients using markdown files and git-synced semantic search.
Lets an AI client semantically search markdown vaults, trace multi-hop note connections, and find hub or orphaned notes.