Memory & Knowledge MCP Servers for DeepSeek Harness

MCP server for Hydra DB: State-of-the-art agentic memory with recall, ingest, and knowledge graph context

Logseq Model Context Protocol Agent

MCP server para Obsidian

Persistent memory for AI agents. Store context, retrieve it semantically.

Local MCP server that indexes your Claude.ai chats and your Claude Code sessions, and exposes them to Claude Code (stdio) and to Claude.ai

Recall past Claude Code conversations from any project as clean, compact Markdown.

Zero-knowledge persistent memory layer for AI agents. Encrypted client-side, hosted in France.

Self-hosted memory layer for AI agents — MCP server backed by Postgres + pgvector + knowledge graph

An elephant never forgets — and neither should your AI. Search and resume past Claude Code conversations via MCP.

MCP ask/question server for Nuwax conversation interaction cards.

Local MCP server for the Remember.md second brain — semantic search + retrieval over your markdown brain.

Persistent memory and session intelligence for AI coding assistants. Zero config.

Task spine + searched dead ends + approvals for AI coding agents. One brain, every device.

Semantic skill routing for SKILL.md libraries, served over MCP to any agent

The memory layer for your AI. Append-only, infinite, never summarised. MCP server for Claude Code, Claude Desktop, Cursor, Windsurf, and

Local-first, source-grounded memory that survives AI agent sessions.

Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.

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

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

Wuniq MCP server. Requires the free Wuniq desktop app. A knowledge engine that keeps decisions, constraints and intent beside your project

Zdravo AI MCP Server — personal and org memory for AI agents