Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Supermemory memories across LLMs
This repo provides an MCP server that exposes Supermemory memories to any MCP client. It is built on the Supermemory API and is meant to make the same memory store available wherever you chat with an agent.
Builders who want their memory store to follow them across Claude Code, Cursor, and other MCP clients.
You can carry remembered context into different LLM tools instead of re-entering the same background again.
What it does
Universal memory access
Makes Supermemory memories available to MCP clients across different LLMs.
No-login setup
The README says you can use it without logging in and with a simple setup flow.
Cloudflare-based app
The repo is set up with Cloudflare worker and Wrangler config for deployment.
Self-hosting support
You can supply `SUPERMEMORY_API_KEY` in `.env` to run your own instance.
README
Supermemory MCP - Universal Memory across LLMs
[!WARNING] MCP v1 is being deprecated. Please get the latest version from app.supermemory.ai. While this repo is maintained and still active, the code for it will be maintained in this moonorepo here https://github.com/supermemoryai/supermemory/tree/main/apps/mcp
Click below for one click install with .dxt
Read a detailed blog about it - https://supermemory.ai/blog/the-ux-and-technicalities-of-awesome-mcps
Your memories are in ChatGPT... But nowhere else. Universal Memory MCP makes your memories available to every single LLM. No logins or paywall. One command to set it up.
Which means you can carry your memories to any MCP client. and it just works!
Demo (Click on the image for video!)
Getting Started
To get started, just visit https://app.supermemory.ai, and follow the instructions on the page.
Features
- 🚀 Built on top of the Supermemory API, extremely fast and scalable.
- ✅ No login required
- 😱 Completely free to use
- Extremely simple setup.
Self-hosting
To self host, get an API key at https://console.supermemory.ai, and then simply add it in the .env file with SUPERMEMORY_API_KEY=
Files in the repo
- app
- public
- workers
- .gitignore
- LICENSE
- package.json
- react-router.config.ts
- README.md
- tsconfig.cloudflare.json
- tsconfig.json
- tsconfig.node.json
- vite.config.ts
- worker-configuration.d.ts
- wrangler.jsonc
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。
