Enterprise DNA Enterprise DNA
M MCP Servers Developer low

eidetic-works/nucleus-mcp

by Various

Nucleus MCP server by Eidetic Works — persistent memory and governance for Claude, Cursor, Windsurf — file-based, no vendor lock-in.

MCP

eidetic-works/nucleus-mcp

Added 26 June 2026

#agent-os #ai-agents #ai-tools #claude #cursor #mcp #mcp-server #model-context-protocol

Overview

An MCP server that provides persistent memory and governance for AI coding assistants including Claude, Cursor, and Windsurf. Uses file-based storage to retain context and rules across sessions, avoiding vendor lock-in. Written in Python and open source.

Best for

Best for
Developers using Claude, Cursor, or Windsurf who want local, persistent memory and governance without vendor lock-in

Use cases

  • Retain long-term project context across Claude, Cursor, and Windsurf sessions
  • Enforce coding guidelines and governance rules consistently in AI interactions
  • Store session memory locally without relying on external cloud services

How to use

Install

npx -y nucleus-mcp

Tools exposed

  • eu-dora
  • sg-mas-trm
  • us-soc2
  • global-default

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT

Notes

An MCP server that provides persistent memory and governance for AI coding assistants including Claude, Cursor, and Windsurf. Uses file-based storage to retain context and rules across sessions, avoiding vendor lock-in. Written in Python and open source.

3 stars on GitHub. Last updated 2026-06-26. Licensed MIT.

Use cases

  • Retain long-term project context across Claude, Cursor, and Windsurf sessions
  • Enforce coding guidelines and governance rules consistently in AI interactions
  • Store session memory locally without relying on external cloud services

Pros

  • Vendor-independent, works across multiple AI coding tools
  • Simple file-based persistence with no external dependencies
  • Open source Python implementation for easy customization

Cons

  • Low adoption (3 stars) suggests limited community and testing
  • File-based storage may not scale well for large teams or complex projects
  • Requires manual setup and configuration by the developer

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Vendor-independent, works across multiple AI coding tools
  • Simple file-based persistence with no external dependencies
  • Open source Python implementation for easy customization

Cons

  • Low adoption (3 stars) suggests limited community and testing
  • File-based storage may not scale well for large teams or complex projects
  • Requires manual setup and configuration by the developer
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks