mcp-server

Memory/Knowledge Graph MCP Server

Persistent memory for AI agents through MCP. Store and retrieve context across conversations using knowledge graphs.

Install
npx -y @anthropic/mcp-server-memory

Overview

Memory MCP servers give AI agents persistent context across conversations. They store facts, relationships, and learned preferences in knowledge graphs that the agent can query. This enables agents to remember user preferences, project context, and prior decisions. However, memory systems are a prime target for memory poisoning attacks -- an attacker who can write to the memory store can permanently influence the agent's behavior.

Features

  • -Key-value fact storage with metadata
  • -Relationship graphs between entities
  • -Temporal memory with decay
  • -Conversation summary persistence
  • -Cross-session context retrieval

Security Considerations

Memory systems are the persistence layer for AI agents. A poisoned memory entry can influence all future interactions. Always validate memory entries before acting on them. Implement memory integrity checks -- if a memory entry seems inconsistent with current reality, verify it before trusting it.

Scan for vulnerabilities: npx hackmyagent secure

Related Tools

Filesystem MCP Server

Read, write, and manage files through the Model Context Protocol. The most commo...

PostgreSQL MCP Server

Query and manage PostgreSQL databases through MCP. Enables AI agents to run SQL ...

Browser/Puppeteer MCP Server

Web browsing capabilities for AI agents through MCP. Navigate pages, click eleme...

Claude Code Security Guide

Security best practices for Claude Code users. Protect your codebase, credential...