Geniffy

io.github.Geniffyv1.0.0Updated Oct 5, 2026

Your memory in every AI app: each fact with the line it came from, or a plain "nothing stored".

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

A hosted memory service that lets connected AI apps search, read, save, correct and forget facts you have told them, each with its source line and date.

What it does
Geniffy is a remote MCP server that gives AI apps a shared memory. Tools include search and fetch for finding facts with the line they came from, ask for answering only from stored memory, profile for lasting facts, list_memories for browsing by kind, and remember, correct and forget for changing what is stored. Facts carry dates, and newer facts replace older ones. When nothing supports an answer, the server says so instead of guessing.
When to use it
Worth adding when you want the same remembered context available across several MCP-capable apps such as Claude, ChatGPT, Cursor, VS Code or Codex, and you want answers traceable to a source line. Less useful if you only need memory inside a single app or do not want your notes stored with a third party.
Requirements
A remote Streamable HTTP endpoint; nothing to install locally. Sign-in is built in via OAuth 2.1, so most apps open a browser sign-in and you approve access. Scripts, CI and browserless agents can instead send a Geniffy API key in the Authorization header. Network access to the hosted service is required.
Before you install
The server stores what you tell it and shares it with every app you connect, so treat it as a third-party copy of your notes. The remember, correct and forget tools change stored memory; you can connect read-only to hide them. Access is granted per app and can be revoked, and requests are logged. API keys used in the Authorization header reach your app's spaces, so keep them secret. Memory is kept in India.

Installation

In SourceWeft

  1. Open Geniffy in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "geniffy-mcp": {
      "type": "http",
      "url": "https://api.geniffy.com/mcp"
    }
  }
}

README

[Geniffy]

Geniffy MCP server

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.

[Docs] [Install in VS Code] [Add to Cursor] [License: MIT]

text
https://api.geniffy.com/mcp

A 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.

Connect your app

AppHow
Claude (Claude.ai and the desktop app)Settings → Connectors → Add custom connector. Name it Geniffy, paste the URL, leave the OAuth fields empty, then Connect and Allow. Guide
ChatGPT (web, developer mode)Settings → Plugins → Developer mode, then Browse plugins → +: name Geniffy, Server URL, paste the URL, Create, Sign in with Geniffy. Guide
Claude CodeThe Geniffy plugin recalls and saves by itself: /plugin marketplace add Geniffy/geniffy-claude-code, /plugin install geniffy@geniffy, /geniffy:login. Or the server alone: claude mcp add --transport http geniffy https://api.geniffy.com/mcp. Guide
CursorOne click from the docs, or the config below. Cursor asks you to sign in the first time it uses Geniffy.
VS CodeThe Install in VS Code badge above, or the config below. VS Code opens the sign-in when it starts the server. Guide
Codexcodex mcp add geniffy --url https://api.geniffy.com/mcp, then codex mcp login geniffy. Guide
Anything elseAdd the URL as a remote HTTP server. Apps that support OAuth open the sign-in by themselves. Guide

Cursor, in ~/.cursor/mcp.json:

json
{  "mcpServers": {    "geniffy": { "url": "https://api.geniffy.com/mcp" }  }}

VS Code, in .vscode/mcp.json:

json
{  "servers": {    "geniffy": { "type": "http", "url": "https://api.geniffy.com/mcp" }  }}

Tools

ToolWhat it doesChanges your memory
searchFinds the facts that match, with where and when each was saidNo
fetchOpens one memory: the exact line it came from, and what it said beforeNo
askAnswers from your memory only, or says that nothing supports an answerNo
profileWhat is lastingly true about you, and what is going on nowNo
list_memoriesYour memories, newest first, by kindNo
rememberSaves something you ask it to rememberYes
correctMarks a memory wrong and saves what is right in its placeYes
forgetForgets one memory, or one source, for goodYes

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.

How it answers

  • 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.

What you control

  • 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.

Sign-in, for client developers

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.

text
https://api.geniffy.com/.well-known/oauth-protected-resource/mcphttps://api.geniffy.com/.well-known/oauth-authorization-server

Without a browser

Scripts, 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.

bash
claude mcp add --transport http geniffy https://api.geniffy.com/mcp \  --header "Authorization: Bearer $GENIFFY_API_KEY"

Build your own app on Geniffy

The MCP server gives the AI apps you use your memory. To give your own app's users a memory, use the API:

Security

Report a vulnerability to [email protected]. Please don't open a public issue for it.

Source: README.md at commit 9e9588e

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 5, 2026