Memory Custom : PouchDB 🧠
This project adds new features to the Memory server offered by the MCP team. It allows for the creation and management of a knowledge graph that captures interactions via a language model (LLM). 🚀
This repo was forked from https://github.com/BRO3886/mcp-memory-custom which was a great starting point, thanks again for fixing timestamps. This repo's goal was more to fix the issue with an ever increasing json file for context.
New Features ✨
1. PouchDB Integration 💾
- The server now uses PouchDB for robust document-based storage
- Why?: Better data consistency, built-in versioning, and improved performance for large datasets
- Maintains file backup for compatibility
2. Custom Memory Paths 📁
- Users can now specify different memory file paths for various projects
- Why?: This feature enhances organization and management of memory data, allowing for project-specific memory storage
3. Timestamping ⏰
- The server now generates timestamps for interactions
- Why?: Timestamps enable tracking of when each memory was created or modified, providing better context and history for the stored data
Getting Started 🚀
Prerequisites 🔧
- Node.js (version 16 or higher)
- PouchDB (automatically installed as a dependency)
Installing via Smithery 📦
To install Knowledge Graph Memory Server for Claude Desktop automatically via Smithery:
Installation 🛠️
- Clone the repository:
- Install the dependencies:
Configuration ⚙️
The server requires two environment variables to be set:
MEMORY_FILE_PATH
: The absolute path where the memory backup file will be storedPOUCHDB_PATH
: The absolute path where the PouchDB database will be stored
Example configuration in your claude_desktop_config.json
/ .cursor/mcp.json
:
The server will fail to start if either environment variable is not set. 🚫
Optional environment variables:
POUCHDB_OPTIONS
: JSON string of additional PouchDB configuration optionsDISABLE_MEMORY_FILE
: Set to "true" to disable saving to memory.json file (only use PouchDB for storage)
Running the Server 🚀
Updating the mcp server json file 📝
Add this to your claude_desktop_config.json
/ .cursor/mcp.json
file:
System Prompt changes:
Running the Server Locally 💻
To start the Knowledge Graph Memory Server, run:
The server will listen for requests via standard input/output.
API Endpoints 🔌
The server exposes several tools that can be called with specific parameters:
- Get Current Time ⏰
- Set Memory File Path 📁
- Create Entities ➕
- Create Relations 🔗
- Add Observations 📝
- Delete Entities ❌
- Delete Observations 🗑️
- Delete Relations 🔗
- Read Graph 📖
- Search Nodes 🔍
- Open Nodes 🔓
Acknowledgments 🙏
- Inspired by the Memory server from Anthropic
- Powered by PouchDB for robust data storage 💾
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
Enhances the MCP memory server by implementing PouchDB for robust document storage and enabling the creation and management of a knowledge graph that captures interactions via language models.
Related MCP Servers
- AsecurityAlicenseAqualityA custom Memory MCP Server that acts as a cache for Infrastructure-as-Code information, allowing users to store, summarize, and manage notes with a custom URI scheme and simple resource handling.Last updated -231PythonMIT License
- AsecurityAlicenseAqualityA high-performance MCP server utilizing libSQL for persistent memory and vector search capabilities, enabling efficient entity management and semantic knowledge storage.Last updated -613363TypeScriptMIT License
- AsecurityFlicenseAqualityThis MCP server provides persistent memory integration for chat applications by utilizing a local knowledge graph to remember user information across interactions.Last updated -955,8555JavaScript
- AsecurityAlicenseAqualityA customized MCP memory server that enables creation and management of a knowledge graph with features like custom memory paths and timestamping for capturing interactions via language models.Last updated -114JavaScriptMIT License