Memory & Knowledge MCP Servers

Query a typed knowledge graph over an Obsidian vault: semantic concept search, contradiction surfacing across reasoning edges, and article

VaultLedger MCP server — the memory tools an AI agent runs

MCP server for graph-aware Obsidian vault traversal

Local-first semantic memory MCP server for Obsidian vaults

MCP server for Markdown/Zettelkasten vaults (Obsidian-compatible) — search, wikilinks, backlinks, and persistent AI memory

Semantic recommendation engine for Obsidian vaults — embeddings + wiki-link graph boosting with MCP server for Claude Code integration.

Blazing-fast local MCP server for Obsidian vault operations via stdio

Local-first MCP memory server for multi-agent systems. Hybrid search (BM25 + semantic embeddings), SQLite-backed, zero-config.

AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node search. By MEOK AI Labs.

A zero-configuration RAG memory server for MCP clients

MCP server for Velixar persistent cognitive context — memory, identity, graph, time, and contradiction for LLMs

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

Official VEM MCP Server for AI agent project memory.

MCP server for the Verbatim platform — collection-aware paper search and RAG

VerifiedState MCP server — verified memory for AI agents via stdio transport

Bookmark and link manager for AI agents with tags, categories, and search. Reads free, writes require Veyra.

Persistent note system with tags and search for AI agents. Reads free, writes require Veyra.

MCP server for VibeCompass — AI project context management

Vidurai — Local-First AI Memory Layer for LLMs. Give Claude, ChatGPT, and Copilot persistent context without cloud sync.

MCP server to visualize Claude conversations as mindmaps

Markdown notes with a first-party MCP server and zero-config local semantic search. The vault your agents can actually use.