# Recall — how to use (mcp.ai)

Recall (recall.it) — your AI knowledge base / 'second brain'. Via the official API: semantic search across your cards, list with filters (tags, dates, source URL) and read a card's content. Read-only (Recall does not expose writes yet). Generate your API key in Settings → API & MCP (Max plan).

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_recall?ms=1784644860000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `recall_list_cards`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/recall`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/recall/_endpoints`

### Endpoints
- `GET https://api.mcp.ai/api/recall/cards` — List Recall cards. Filters: tags[] (UUIDs), date_from/date_to (ISO 8601), source_url_contains.
  - body: { tags?: string[], date_from?: string, date_to?: string, source_url_contains?: string }
- `GET https://api.mcp.ai/api/recall/cards/{card_id}` — Card content (chunks). focus_query focuses chunks; max_chunks (1-50).
  - body: { card_id: string, focus_query?: string, max_chunks?: integer }
- `GET https://api.mcp.ai/api/recall/search` — Semantic search. q required; mode focused|exhaustive; filters card_id/tags/dates/source_url_contains.
  - body: { q: string, mode?: string, card_id?: string, tags?: string[], date_from?: string, date_to?: string, source_url_contains?: string }

## Example prompts
- "Search my Recall for what I saved about spaced repetition"
- "List my cards from the last month"
- "Get the content of card X focusing on 'pricing'"

## More
- Page: https://mcp.ai/recall
- Agent spec (llms.txt): https://mcp.ai/recall/llms.txt
- Postman collection: https://mcp.ai/recall/postman.json