
MCP Knowledge Graph
The Mcp Knowledge Graph server provides persistent memory for AI models by storing and retrieving information across conversations through a local knowledge graph using entities, relations, and observations. It offers tools to manage a master database (default memory store) and optional topic-specific databases, with automatic project-local storage in `.aim` directories and configurable global fallback locations. The system includes safety mechanisms with file markers to prevent accidental overwrites and works with Claude Code/Desktop and any MCP-compatible AI platform.
- GitHub stars
- 857
- tools
- 10
- last updated
- Dec 15, 2025
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
aim_memory_storeStore new memories (people, projects, concepts)
Store new memories (people, projects, concepts)
No parameter schema in public metadata yet.
aim_memory_add_factsAdd facts to existing memories
Add facts to existing memories
No parameter schema in public metadata yet.
aim_memory_linkLink two memories together
Link two memories together
No parameter schema in public metadata yet.
aim_memory_searchSearch memories by keyword
Search memories by keyword
No parameter schema in public metadata yet.
aim_memory_getRetrieve specific memories by exact name
Retrieve specific memories by exact name
No parameter schema in public metadata yet.
aim_memory_read_allRead all memories in a database
Read all memories in a database
No parameter schema in public metadata yet.
aim_memory_list_storesList available databases
List available databases
No parameter schema in public metadata yet.
aim_memory_forgetForget memories
Forget memories
No parameter schema in public metadata yet.
aim_memory_remove_factsRemove specific facts from a memory
Remove specific facts from a memory
No parameter schema in public metadata yet.
aim_memory_unlinkRemove links between memories
Remove links between memories
No parameter schema in public metadata yet.
Sponsors
Readme
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:
.aimdirectories: Keep AI memory files organized and easily identifiableaim_tool prefixes: Group related memory functions together in multi-tool setups_aimsafety markers: Each memory file starts with{"type":"_aim","source":"mcp-knowledge-graph"}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 .aim dir vs _aim file marker
Two different things with similar names:
.aim= Project-local directory name (MUST be named exactly.aimfor project detection to work)_aim= File safety marker (appears inside JSONL files:{"type":"_aim","source":"mcp-knowledge-graph"})
Details
- Repository
- github.com/shaneholloman/mcp-knowledge-graph
- Categories
- AI & LLM Tools, Documents & Knowledge