MCP.so
Sign In
M

MindCore Memory MCP

@woshilaohei

About MindCore Memory MCP

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.

Basic information

Category

Memory & Knowledge

Transports

stdio

Publisher

woshilaohei

Submitted by

woshilaohei

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mindcore-memory": {
      "command": "python",
      "args": [
        "-m",
        "mindcore_memory"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Mindcore Memory Mcp?

Mindcore Memory Mcp is an AI long-term memory server that provides production-grade persistent memory for AI agents. It integrates with any MCP-compatible client (Claude Desktop, Cursor, Cline, etc.) via stdio transport and uses an embedded TinyDB database, requiring no external infrastructure.

How to use Mindcore Memory Mcp?

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.

Key features of Mindcore Memory Mcp?

  • 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

Use cases of Mindcore Memory Mcp?

  • Maintain user preferences and schedules across AI agent sessions
  • Store and retrieve project architecture decisions without re-teaching
  • Build precise context windows for complex queries without overload
  • Accumulate knowledge over time for continuous learning agents

FAQ from Mindcore Memory Mcp

What does Mindcore Memory Mcp use for storage?

It uses TinyDB, an embedded database that stores memories locally as JSON files. No PostgreSQL, Redis, or vector database is required.

What are the runtime requirements?

Python 3.10 or higher. No external database or additional services are needed.

How are memories ranked when recalled?

Memories are ranked by a scoring engine that combines importance, confidence, recency, and relevance to the query.

What transport protocol does Mindcore Memory Mcp use?

It implements the Model Context Protocol (MCP) over stdio transport.

Is there any limit on the number of memories?

The

Comments

More Memory & Knowledge MCP servers