MindCore Memory MCP
About
AI long-term memory MCP server with importance scoring and confidence calibration. Enables AI agents to store, search, and retrieve long-term memories with semantic similarity and importance-weighted recall.
Details
- Author
- woshilaohei
- Downloads
- 248
- Categories
- AI, Knowledge Base, Other
Jump to
- Zero external dependencies (embedded TinyDB)
- Importance grading (1–4) and confidence scoring
- Smart pruning and context window construction
- Deduplication and ranking by relevance × importance × confidence
- Six core tools: store, recall, context, update, delete, stats
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MindCore Memory MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via pip (pip install mindcore-memory), then launch the MCP server with the mindcore-memory command. Configure the MCP client with the command python -m mindcore_memory.server in its settings. Once connected, call tools such as memory_store, memory_recall, memory_context, memory_update, memory_delete, and memory_stats to manage memories.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mindcore memory mcp": {
"mindcore-memory": {
"command": "python",
"args": [
"-m",
"mindcore_memory"
]
}
}
}
}McpServers
{
"mindcore-memory": {
"command": "python",
"args": [
"-m",
"mindcore_memory"
]
}
}MindCore Memory MCP
<!-- MCP Registry ownership verification -->
mcp-name: io.github.woshilaohei/mindcore-memory
AI Long-Term Memory Server — Production-grade persistent memory for AI agents.
> "The best AI agent isn't the smartest — it's the one that remembers."
Table of Contents
- Why MindCore Memory
- Quick Start
- Installation
- MCP Client Setup
- Core Tools
- Eval Results
- Architecture
- Development
- License
Why MindCore Memory
AI agents today face a fundamental limitation: they forget everything between sessions.
| Pain Point | Without Memory | With MindCore Memory |
|------------|---------------|---------------------|
| Session Amnesia | Re-teach every conversation | Persistent cross-session recall |
| Memory Overload | All memories equal weight, context explodes | Importance grading + smart pruning |
| RAG Failure | Brute-force injection, quality degrades | Precision context window construction |
| Zero Continuity | Every session starts from scratch | Knowledge accumulates over time |
MindCore Memory is the missing persistence layer for AI agents. Built as an MCP server, it plugs into any MCP-compatible client (Claude Desktop, Cursor, Cline, etc.) with zero configuration changes.
Quick Start
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
