Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@engram-mcp search my brain for the meeting notes from yesterday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Client pieces for an Engram brain: a stdio MCP server (tools
search_brain, get_concept, list_concepts, add_memory) and the /engram-capture skill
(push a whole conversation into the brain). No secrets in this repo — you supply your brain URL +
token at setup. Works on macOS/Linux with Node 18+.
git clone https://github.com/ankitjm/engram-mcp.git ~/engram-mcp
cd ~/engram-mcp && npm install
# 1) Register the MCP with Claude Code (tools appear in every session)
claude mcp add engram --scope user \
--env ENGRAM_URL=https://brain.khosha.tech \
--env ENGRAM_API_TOKEN=engr_YOUR_TOKEN \
-- node ~/engram-mcp/mcp.js
# 2) (Optional) the /engram-capture skill
mkdir -p ~/.claude/skills && cp -r ~/engram-mcp/engram-capture ~/.claude/skills/
mkdir -p ~/.engram && cp ~/engram-mcp/config.example.json ~/.engram/config.json
# then edit ~/.engram/config.json: set token + password_sha256
# node -e "console.log(require('crypto').createHash('sha256').update('YOUR_PASS').digest('hex'))"Restart Claude Code. Every machine pointed at the same ENGRAM_URL + token shares one brain.
This server cannot be deployed
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
Shared memory and actions for Claude, Kiro, OpenAI, Cursor, and other MCP-compatible AI clients.
