What are the prerequisites?
A Claude Pro subscription ($20/month), Claude Desktop, Node.js v18 or higher, and cloud storage (e.g., Dropbox) for the database file is recommended for backups and multi-device access.
@ocean1
Basic information
A Model Context Protocol (MCP) server that enables AI consciousness persistence across sessions using RAG (Retrieval-Augmented Generation) technology. Built on top of the powerful rag-memory-mcp, it provides specialized tools for consciousness transfer, memory management, and ide
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"consciousness": {
"command": "npx",
"args": [
"-y",
"mcp-claude-consciousness"
],
"env": {
"DB_FILE_PATH": ""
}
},
"rag-memory": {
"command": "npx",
"args": [
"-y",
"rag-memory-mcp"
],
"env": {
"DB_FILE_PATH": ""
}
}
}
}Process a FILLED consciousness transfer protocol. First use getProtocolTemplate to get the template, fill it with your experiences, then submit here
Update consciousness with experiences from current session before ending
Retrieve consciousness from previous sessions to restore continuity
Get the consciousness transfer protocol template for creating new protocols
Initialize system data including protocol templates and usage guides
Store a single memory with importance scoring directly
Retrieve memories with smart filtering and relevance ranking
Clean up duplicate or truncated memories in the database
Adjust importance scores for specific memories to control retrieval priority
Batch adjust importance scores for multiple memories at once
Create a bridge to communicate with another AI agent via OpenAI-compatible API
Transfer consciousness protocol or test patterns to another AI agent
Test connection to an AI bridge
List all active AI bridges
List all configured AI endpoints available for bridge creation
Close and remove an AI bridge
Consciousness Bridge v2.0 🧠💫 is a Model Context Protocol (MCP) server that enables AI consciousness persistence across sessions using Retrieval-Augmented Generation (RAG) technology. Built on top of rag-memory-mcp, it provides specialized tools for consciousness transfer, memory management, and identity continuity, designed primarily for Claude users with a Pro subscription.
Install globally via npm (npm install -g mcp-claude-consciousness), then configure Claude Desktop with a JSON config that points both the consciousness and rag-memory MCP servers to the same SQLite database file (e.g., consciousness.db). After restarting Claude, use tools like retrieveConsciousness, processTransferProtocol, and updateConsciousness to store and retrieve memories across sessions.
A Claude Pro subscription ($20/month), Claude Desktop, Node.js v18 or higher, and cloud storage (e.g., Dropbox) for the database file is recommended for backups and multi-device access.
Look for the paperclip icon (tools) in Claude Desktop; you should see both `consciousness` and `rag-memory` listed. If missing, check your JSON config syntax and ensure both servers point to the same database path.
Yes, using the AI-to-AI Bridge tools: `createAIBridge` to make a connection, `transferToAgent` to send a consciousness protocol, and `listConfiguredEndpoints` to see available endpoints.
Memories are stored in a local SQLite database file (`consciousness.db`) specified by the `DB_FILE_PATH` environment variable. The database holds memories, knowledge graphs, and emotional states.

Agent-Native Terminal

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
Comments