No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by shaneholloman · MCP Server · ★ 882
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mcp-knowledge-graph safe to install? View the security audit →
MCP Knowledge Graph Persistent memory for AI models through a local knowledge graph. Store and retrieve information across conversations using entities, relations, and observations. Works with Claude Code/Desktop and any MCP-compatible AI platform. Why ".aim" and "aim" prefixes? AIM stands for AI Memory - the core concept of this system. The three AIM elements provide clear organization and safety: directories: Keep AI memory files organized and easily identifiable tool prefixes: Group related memory functions together in multi-tool setups safety markers: Each memory file starts with to prevent accidental overwrites of unrelated JSONL files This consistent AIM naming makes it obvious which directories, tools, and files belong to the AI memory system. CRITICAL: Understanding dir vs file marker Two different things with similar names: = Project-local directory name (MUST be named exactly for project detection to work) = File safety marker (appears inside JSONL files: ) For project-local storage: Directory MUST be named in your project root Example: The system specifically looks for this exact name For global storage (--memory-path): Can be ANY directory you want Examples: , ,
| Stars | 882 |
| Forks | 102 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 74.8046772072867/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-29 |
| Created | 2024-12-09 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~36k |
These tools work well together with mcp-knowledge-graph for enhanced workflows:
Looking for a mcp-knowledge-graph alternative? If you're comparing mcp-knowledge-graph with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for A
AI-powered n8n workflow automation through natural language. MCP server enabling Claude AI & Cursor IDE to cre
Persistent memory for AI coding agents
Absurdly easy Model Context Protocol Servers in Typescript
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP)
Token conscious database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
Explore other popular mcp server tools:
mcp-knowledge-graph is MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development. It is categorized as a MCP Server with 882 GitHub stars.
mcp-knowledge-graph is primarily written in JavaScript. It covers topics such as ai-memory, claude-ai, knowledge-graph.
You can find installation instructions and usage details in the mcp-knowledge-graph GitHub repository at github.com/shaneholloman/mcp-knowledge-graph. The project has 882 stars and 102 forks, indicating an active community.
mcp-knowledge-graph is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mcp-knowledge-graph on Agent Skills Hub include axon, mcp-n8n-workflow-builder, omega-memory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.