mcp-knowledge-graph
MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
The mcp-knowledge-graph MCP server provides persistent memory for AI assistants through a local knowledge graph stored in JSONL files. It enables Claude and other MCP-compatible platforms to remember entities, relationships, and observations across conversations using a system of project-local or global memory databases. The server uses an "AIM" (AI Memory) naming convention with `.aim` directories and safety markers to organize memory files. Developers can configure a master database for default operations plus optional named databases (work, personal, health) to organize memories by topic, with automatic project detection when a `.aim` folder exists.
Key Features
Use Cases
- 01Maintaining conversation context and memory across multiple Claude Desktop sessions
- 02Organizing work-related knowledge separately from personal memories using named databases
- 03Creating project-specific knowledge graphs that travel with repository code
- 04Syncing AI memories across multiple machines via cloud storage providers
- 05Building persistent knowledge bases for long-running research or development projects
- 06Storing and linking related entities like people, projects, and concepts with observations
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
mcp-knowledge-graph — FAQ
What is mcp-knowledge-graph?+
It's an MCP server that gives AI assistants like Claude persistent memory by storing entities, relationships, and observations in a local knowledge graph using JSONL files. It supports both project-local storage via `.aim` directories and global memory paths.
How do I install mcp-knowledge-graph in Claude Desktop?+
Add a configuration block to your `claude_desktop_config.json` with the command `npx` and args `["-y", "mcp-knowledge-graph", "--memory-path", "/Users/yourusername/.aim"]`. Restart Claude Desktop after saving the config file.
Which AI clients work with this MCP server?+
It works with Claude Desktop, Claude Code, and any MCP-compatible AI platform. The README specifically mentions these clients as tested integrations.
Do I need API keys or external services?+
No, this server stores all memory data locally in JSONL files on your filesystem. It requires Node.js 22+ but no external APIs or cloud services.
Is mcp-knowledge-graph free to use?+
Yes, it's open source and released under the MIT license, making it free for both personal and commercial use.
What's the difference between project-local and global memory?+
Project-local memory stores data in a `.aim` folder within your project directory, while global memory uses a configured path (like `~/yourusername/.aim`) that persists across all projects. The server automatically uses project-local storage when it detects a `.aim` directory.
How do I install mcp-knowledge-graph?+
Open the source repository on GitHub and follow its README. mcp-knowledge-graph is a mcp server — MCP Agents Market links you directly to the official repo.
Is mcp-knowledge-graph free?+
mcp-knowledge-graph is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.