Memory & Knowledge MCP Servers for Claude Code

A local MCP server that exposes your Obsidian vault as structured tools for Claude.ai

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

Shared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol.

Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.

Persistent shared memory for AI agents, with verified writes and a transcript tier.

Team-aware memory for Claude Code, Cursor, and other AI coding assistants — intent tracking, decision history, real-time team conflict

Coding agents build full-stack apps in persistent workspaces and share them by link.

Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.

cite-citadel — an LLM-maintained, fully-cited personal wiki in the Open Knowledge Format, fed by a coding-agent CLI you already have logged

MCP server for Cortex memory service — persistent memory for AI agents

A lightweight, structured, token-efficient local-first MCP memory server

Readwise MCP

Persistent project memory for AI coding agents — semantic search, AST-aware chunking, dependency graphs, and conversation history

Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.

Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.

Evidence-backed, explainable persistent memory for MCP-compatible AI agents.

MCP server for Logseq: graphs, pages, blocks via the local HTTP API plugin.

MCP server for systematic thinking, mental models, debugging approaches, and memory management

Fodda MCP Server for accessing knowledge graph insights.

Local-first memory for AI agents that reaches backward to find a failure's root cause.

FAVA Trails 🫛👣 — Federated Agents Versioned Audit Trail. VCS-backed memory for AI agents via MCP.