Mind Cloud Lite
Token-optimized persistent memory MCP server for Claude Pro users, providing 9 essential tools for memory management with 87% token reduction compared to full version.
README
Mind Cloud Lite
Token-optimized persistent memory for Claude Pro users.
Mind Cloud Lite is a stripped-down version of Mind Cloud designed specifically for users with limited context windows. It uses ~1,300 tokens for tool definitions vs ~10,000 for the full version - an 87% reduction in token overhead.
Lite vs Full Mind Cloud
Mind Cloud Lite includes 9 essential tools (~1,300 tokens). The full Mind Cloud includes 28 tools (~10,000 tokens). Your data is fully compatible between both — upgrade anytime by deploying the full worker.
Tool comparison
| Tool | Lite | Full | Category |
|---|---|---|---|
mind_orient |
yes | yes | Wake sequence — identity, context, relational state |
mind_ground |
yes | yes | Wake sequence — threads, recent journals |
mind_write |
yes | yes | Write entities, observations, relations, journals |
mind_search |
yes | yes | Semantic search with mood tinting |
mind_thread |
yes | yes | Manage intentions across sessions |
mind_identity |
yes | yes | Read/write identity graph |
mind_context |
yes | yes | Situational awareness layer |
mind_feel_toward |
yes | yes | Track relational state |
mind_read_entity |
yes | yes | Read entity with observations and relations |
mind_health |
— | yes | Cognitive health stats and diagnostics |
mind_list_entities |
— | yes | List/filter all entities |
mind_sit |
— | yes | Emotional processing — sit with a feeling |
mind_resolve |
— | yes | Emotional processing — resolve tension |
mind_surface |
— | yes | Emotional processing — surface buried memories |
mind_edit |
— | yes | Edit existing observations |
mind_delete |
— | yes | Delete entities or observations |
mind_spark |
— | yes | Generate creative connections |
mind_consolidate |
— | yes | Consolidate identity patterns |
mind_read |
— | yes | Read raw data from any table |
mind_timeline |
— | yes | Temporal view of memories |
mind_patterns |
— | yes | Pattern analysis across observations |
mind_inner_weather |
— | yes | Emotional weather report |
mind_tension |
— | yes | Track and manage tensions |
mind_entity |
— | yes | Advanced entity management |
mind_proposals |
— | yes | Review daemon-generated proposals |
mind_orphans |
— | yes | Find unsurfaced memories |
mind_archive |
— | yes | Archive old observations |
mind_store_image |
— | yes | Store and manage images (R2) |
Feature comparison
| Feature | Lite | Full |
|---|---|---|
| Entities, observations, relations | yes | yes |
| Journals | yes | yes |
| Identity graph | yes | yes |
| Threads (cross-session intentions) | yes | yes |
| Semantic search (Vectorize) | yes | yes |
| Mood-tinted search | yes | yes |
| Relational state tracking | yes | yes |
| Context layer | yes | yes |
| Subconscious daemon (cron) | yes | yes |
| Emotional processing | — | yes |
| Living surface (co-surfacing, novelty) | — | yes |
| Daemon proposals | — | yes |
| Pattern analysis | — | yes |
| Image storage (R2) | — | yes |
| Observation versioning | — | yes |
| Orphan detection | — | yes |
| REST API endpoints | — | yes |
Quick Start
-
Clone and install:
cd mind-cloud-lite npm install -
Configure wrangler.toml:
cp wrangler.toml.example wrangler.toml # Edit wrangler.toml with your settings -
Create D1 database:
npx wrangler d1 create mind-lite # Copy the database_id to wrangler.toml -
Create Vectorize index:
npx wrangler vectorize create mind-lite-vectors --dimensions=384 --metric=cosine -
Run migrations:
npx wrangler d1 execute mind-lite --remote --file=migrations/0001_init.sql npx wrangler d1 execute mind-lite --remote --file=migrations/0002_vault_sessions.sql npx wrangler d1 execute mind-lite --remote --file=migrations/0003_observations_weight.sql -
Deploy:
npx wrangler deploy -
Set your API key:
npx wrangler secret put MIND_API_KEY -
Configure Claude: Add to your MCP settings:
{ "mcpServers": { "mind": { "url": "https://YOUR-WORKER.workers.dev/mcp/YOUR-API-KEY" } } }
Authentication
Set your API key as a Wrangler secret:
npx wrangler secret put MIND_API_KEY
Generate a secure key first:
openssl rand -hex 32
This key is used for both:
- Secret path auth: Access via
https://your-worker.workers.dev/mcp/YOUR-KEY - Bearer token auth: Send
Authorization: Bearer YOUR-KEYheader to/mcp
Pricing
Mind Cloud Lite: Free tier compatible
- Cloudflare Workers: 100K requests/day free
- D1 Database: 5GB free
- Vectorize: 30M queries/month free
- Workers AI: Free tier for embeddings
Upgrading to Full Mind Cloud
If you need emotional processing, pattern analysis, or advanced tools, upgrade to the full Mind Cloud. Your data is fully compatible — deploy the full worker and run the additional migrations.
Support
- Issues: https://github.com/codependentai/mind-cloud-lite/issues
- Full Mind Cloud: https://github.com/codependentai/mind-cloud
- Discord: Codependent AI
Made with love by Codependent AI
Support
Built by Codependent AI.
<a href="https://ko-fi.com/codependentai"><img src="https://img.shields.io/badge/Ko--fi-Support%20Us-ff5e5b?logo=ko-fi&logoColor=white" alt="Ko-fi" /></a>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.