Cursor is fantastic at the edit-and-explain loop, but the agent forgets everything between sessions. You can paste the same project context into chat ten times a day and still rediscover the same gotchas tomorrow.
The fix is small and concrete: give Cursor an MCP server that owns your long-term memory. dropdat's MCP server lets Cursor read any capsule you've captured from any AI app — across all your projects.
What you get
- dropdat_recall — keyword search over every capsule you've saved.
- dropdat_read — pull a specific capsule's full contents into the model's context.
- dropdat_list — browse recent capsules by tag.
- dropdat_capsule — let the agent save the current conversation back to your library.
Setup (60 seconds)
- Install the dropdat browser extension and capture at least one chat.
- Generate an API key at dropdat.app/api-keys (`dk_live_…`).
- In Cursor, open MCP settings and add the dropdat server.
{
"mcpServers": {
"dropdat": {
"command": "npx",
"args": ["-y", "@dropdat/mcp"],
"env": { "DROPDAT_API_KEY": "dk_live_…" }
}
}
}Example prompts
- “Use dropdat_recall to find the migration discussion from yesterday and apply it to api/internal/db.”
- “List my recent capsules tagged 'auth' and summarize the open questions.”
- “Pull the full Claude chat about the rate-limit bug — read it with dropdat_read and propose a fix.”
Why this works better than @-mentioning files
File context tells Cursor *what* the code is. Capsule recall tells Cursor *what you and another AI already decided*. That's a much higher-signal slice of context — and it's the part that usually lives in a Slack message or a ChatGPT tab you closed three days ago.