# threadline-mcp

MCP server for [Threadline](https://www.threadline.to) — the memory governance layer for AI agents.

Use Threadline's persistent, user-consented memory in any MCP-compatible client: Cursor, Claude Desktop, or your own agent.

## Install

```bash
npm install -g threadline-mcp
```

## Setup

Get your API key at [threadline.to/dashboard](https://www.threadline.to/dashboard).

### Claude Desktop

Add to `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "threadline": {
      "command": "threadline-mcp",
      "env": {
        "THREADLINE_API_KEY": "tl_live_your_key_here"
      }
    }
  }
}
```

### Cursor

Add to your MCP config in Cursor settings:

```json
{
  "threadline": {
    "command": "threadline-mcp",
    "env": {
      "THREADLINE_API_KEY": "tl_live_your_key_here"
    }
  }
}
```

### Any MCP client

```bash
THREADLINE_API_KEY=tl_live_your_key_here threadline-mcp
```

## Tools

### `inject`

Inject user context into a base system prompt before an LLM call.

```json
{
  "userId": "user-uuid",
  "basePrompt": "You are a helpful assistant."
}
```

Returns an enriched prompt with relevant facts about the user automatically inserted.

### `update`

Update a user's context after an LLM interaction. Extracts and stores structured facts for future sessions.

```json
{
  "userId": "user-uuid",
  "userMessage": "I prefer concise answers and I'm building in TypeScript.",
  "agentResponse": "Got it, keeping it brief."
}
```

## How it works

```
Your MCP client (Cursor / Claude Desktop)
        │
        ▼
threadline-mcp (this package)
        │
        ▼
api.threadline.to
        │
   ┌────┴────┐
   ▼         ▼
Supabase   Redis
(context)  (<50ms)
```

- `inject()` — fetches stored context, scores by recency + relevance, returns enriched prompt
- `update()` — two-stage extraction pipeline classifies and stores new facts across 7 scopes

## Links

- Docs: [threadline.to/docs](https://www.threadline.to/docs)
- Dashboard: [threadline.to/dashboard](https://www.threadline.to/dashboard)
- Support: vidur@threadline.to