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., "@Geniffy MCP Server what did I tell ChatGPT about the Q3 launch deadline?"
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.
Your memory inside Claude, ChatGPT, Cursor, VS Code, Codex and any app that speaks MCP. Tell one of them something, and every app you connect can find it, with the line it came from and the date it was said.
https://api.geniffy.com/mcpA hosted, remote MCP server (Streamable HTTP) with sign-in built in: there is nothing to install and no key to copy. Add the URL to your app, sign in to Geniffy when it asks, and choose what the app may do.
Listed in the official MCP Registry
as io.github.Geniffy/geniffy-mcp.
App | How |
Claude (Claude.ai and the desktop app) | Settings → Connectors → Add custom connector. Name it |
ChatGPT (web, developer mode) | Settings → Plugins → Developer mode, then Browse plugins → +: name |
Claude Code | The Geniffy plugin recalls and saves by itself: |
Cursor | One click from the docs, or the config below. Cursor asks you to sign in the first time it uses Geniffy. |
VS Code | The Install in VS Code badge above, or the config below. VS Code opens the sign-in when it starts the server. Guide |
Codex |
|
Anything else | Add the URL as a remote HTTP server. Apps that support OAuth open the sign-in by themselves. Guide |
Cursor, in ~/.cursor/mcp.json:
{
"mcpServers": {
"geniffy": { "url": "https://api.geniffy.com/mcp" }
}
}VS Code, in .vscode/mcp.json:
{
"servers": {
"geniffy": { "type": "http", "url": "https://api.geniffy.com/mcp" }
}
}Related MCP server: CyberMem
Tool | What it does | Changes your memory |
| Finds the facts that match, with where and when each was said | No |
| Opens one memory: the exact line it came from, and what it said before | No |
| Answers from your memory only, or says that nothing supports an answer | No |
| What is lastingly true about you, and what is going on now | No |
| Your memories, newest first, by kind | No |
| Saves something you ask it to remember | Yes |
| Marks a memory wrong and saves what is right in its place | Yes |
| Forgets one memory, or one source, for good | Yes |
Every tool has an input schema, an output schema and annotations that say whether it changes your memory.
search and fetch return the shape ChatGPT's connectors read. Inputs and results:
docs.geniffy.com/mcp/tools.
With its source. Every fact comes back with the line it was read from, who said it and when.
Or not at all. When nothing in your memory supports an answer, Geniffy says so, and the app is told to say it doesn't know rather than guess.
With today's truth. Facts carry dates. When something changes, the newer fact replaces the older one.
You approve each app. Geniffy shows who is asking and where it will send you back. Nothing is shared until you press Allow.
Read, or read and change. Turn off saving when you connect, and the app never sees the tools that change your memory.
Disconnect at any time in the Geniffy app under Agents and MCP. Every call an app makes is listed under Requests, with its name.
Your memory stays in India, where Geniffy keeps it.
OAuth 2.1, following the MCP authorization specification: a 401 with WWW-Authenticate names the
protected-resource metadata (RFC 9728), which points to the authorization server metadata (RFC 8414).
Dynamic client registration (RFC 7591), PKCE with S256 only, scopes memory:read and memory:write,
hourly access tokens, rotating refresh tokens, revocation (RFC 7009) and the iss response parameter
(RFC 9207). Details: docs.geniffy.com/mcp/sign-in.
https://api.geniffy.com/.well-known/oauth-protected-resource/mcp
https://api.geniffy.com/.well-known/oauth-authorization-serverScripts, CI and agents that cannot open a browser can send a Geniffy API key as a header. A key reaches
your app's spaces too: every tool then takes an optional space.
claude mcp add --transport http geniffy https://api.geniffy.com/mcp \
--header "Authorization: Bearer $GENIFFY_API_KEY"The MCP server gives the AI apps you use your memory. To give your own app's users a memory, use the API:
Python: pip install geniffy
TypeScript and JavaScript: npm install geniffy
Runnable examples: Geniffy/examples
Docs: docs.geniffy.com
Report a vulnerability to ops@geniffy.com. Please don't open a public issue for it.
This server cannot be deployed
Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.
AI memory layer — one shared, persistent memory across every AI tool you connect.
Portable AI memory you own. Keep memories and notes across Claude, ChatGPT, and other AI tools.
Cross-model memory for people and teams: one memory every AI you use loads at session start.
