Give Claude Code a memory of your screen with Sharpy MCP

You open Claude Code, and the first five minutes go to explaining. What the gateway decision was on Wednesday. What the client asked for in the Telegram thread. Which of the three approaches you tried yesterday and rejected. The agent is capable and blank.

Sharpy fixes the blank part. It already remembers the text your Mac showed you, in one SQLite file on the machine. The MCP server hands that memory to the agent.

One command

claude mcp add sharpy -- /Applications/Sharpy.app/Contents/Helpers/sharpy-mcp

Then, on the first connection, approve the client inside the Sharpy app. That is the whole setup for Claude Code. Cursor and Claude Desktop take the same binary in their MCP configuration, as a stdio server with no arguments.

The server runs locally and reads the same database the app writes. There is no second copy, no sync, no account for the MCP itself. Sharpy.app has to be running; reading works even signed out, capture does not. By default a client gets the first 1,000 characters of a passage; full text for that client is a switch in Settings → Integrations.

What the agent can now do

The server exposes a handful of tools. In practice you never call them; you ask, and the agent picks.

• search_memory. Full-text search over everything captured, with a from/to window and an app filter. “Find where we agreed on the retry policy” returns the matching passages, each with its snapshot and session id, app, window title, URL and time.
• get_recent_activity. The last minutes of screen activity, newest first: app, window, URL, seconds spent, an excerpt. No model involved, so it is the cheapest call. Made for “what was I just doing?”.
• get_working_memory. The sessions of the last few hours (three by default) with the full text of the latest moment in each. The agent reads this to orient before it searches, or to load your context before writing in your voice.
• read_session. One continuous stretch of work end to end: a whole email thread, a Slack channel, a coding session.
• get_snapshots. The full text of specific moments by id, for quoting exact wording, numbers and dates.
• wiki search. The pages Sharpy maintains about people and projects, built from captured text with citations.

Every row carries a snapshot id. When the agent tells you “you agreed on Thursday 18:00”, it can open that exact moment and quote it, and so can you, in Sharpy.

Three ways people use it

Stop re-explaining. Start a session with “read my working memory, then plan the migration we discussed in Slack this morning”. The agent reads those sessions, searches for the Slack thread, and plans from what was said, not from your retelling of it.

Turn conversations into tickets. “Search the last two days for anything Dana asked me to do and write the issues.” The agent finds the requests in Telegram and Mail, quotes them, and drafts.

Debug from what you saw. You hit an error at 14:07, took a screenshot in your head, and moved on. “What was the error I saw in the terminal around two o’clock?” The text was captured; the agent finds it.

Limits worth knowing

Sharpy captures the front window through macOS Accessibility. Native apps read well. Electron apps, which is most AI desktop clients and many chat apps, expose their text less cleanly, so some passages will be missing or partial. If a search comes back thin, the browser version of the same app usually reads better.

What the agent pulls into its context leaves the Mac with that context. Claude Code sends it to Anthropic; Cursor sends it to whatever model you picked. Sharpy itself masks card numbers, IBANs and tokens before they are stored, and never captures banks, password fields, login pages or incognito windows. Narrow questions keep the rest narrow.

Sharpy is macOS 14 or later, by invite. If your day is Claude Code plus Telegram plus a browser, get on the list and mention it in the reply to the welcome email; developers go early.