# ClariLayer

ClariLayer saves selected decisions and work preferences for AI to recall across projects and sessions. Connecting the server alone does not ensure the client will use that context.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 76
- Author: clarilayer
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/clarilayer/clarilayer
- Updated: 2026-09-17
- HTML: https://affpapa.org/en/nevibecode/mcp/clarilayer

## What it does

ClariLayer stores the facts, rules, decisions, and lessons you choose to carry forward. The AI can search an authorized space with `recall_context`, save confirmed information with `remember`, and open a full record with `get_context_entry`. To change or remove an entry, first retrieve it and use its ID.

Connect over HTTP, then finish authentication in your client. At the first relevant use in a new session, the installed setup can retrieve current workflow guidance. MCP connection alone does not make the AI consult saved context; the client has to call the server tool.

History import is a separate flow: review a preview before accepting it, and grant access separately for ongoing capture. The chosen extraction provider processes imported material; ClariLayer keeps extracted context rather than raw transcript archives. Semantic search needs separate organization consent, while lexical recall remains available without it.

## Requirements
- Remote server: `https://clarilayer.com/api/mcp/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http clarilayer https://clarilayer.com/api/mcp/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add clarilayer --url https://clarilayer.com/api/mcp/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "clarilayer": {
            "url": "https://clarilayer.com/api/mcp/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "clarilayer": {
            "type": "http",
            "url": "https://clarilayer.com/api/mcp/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http clarilayer https://clarilayer.com/api/mcp/mcp
```

## When to use it
- carry a confirmed decision into a later session
- retrieve project context before drafting a page
- save a durable work preference or rule
- check the source and scope of a saved entry
- correct or remove a specific memory

## Example prompts
- Recall the Launch project's decisions before drafting the page, and show each source.
- Save this confirmed project rule and identify where it applies.
- Find the Launch decision entry and remove it using its ID.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md