# icontext

> icontext — floomhq-icontext. Use this tool when you need to securely store and retrieve AI context from various sources, such as Gmail and LinkedIn, to provide persistent memory for Claude Code, Codex, and Cursor. It solves the problem of limited AI context retention by encrypting and storing relevant information, allowing for more informed and personalized interactions. The tool takes in data from Gmail and LinkedIn as input and outputs a secure, encrypted context vault accessible via git.

Canonical page: https://skillsregistry.net/skills/floomhq-icontext  
JSON: https://api.skillsregistry.net/v1/skills/floomhq-icontext

## Description

Encrypted AI context vault: give Claude Code, Codex, and Cursor persistent memory from Gmail + LinkedIn

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** communication
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/floomhq/icontext)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "floomhq-icontext"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/floomhq-icontext` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/floomhq-icontext/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt