A Python library for interfacing with the Rewind.ai SQLite database.
A Python library for interfacing with the Rewind.ai SQLite database. The rewindmcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 8 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
Parameters — time_period (required, e.g., '1hour', '30minutes', '1day', '1week'), application (optional, filter by app name)Returns — Frame count per application, OCR node count (activity level), number of unique windows, time range when application was active, sorted by activityPrerequisites — The Prerequisites tool exposed by this serverFrames — Screenshots captured by Rewind.ai at regular intervals as you use your computer. Each frame in the frame table includes a timestamp (createdAt) andNodes — Text elements extracted from screen captures using Optical Character Recognition (OCR). Each node in the node table represents a piece of textSearchRanking_Content — This table stores the actual OCR text content extracted from screen captures. It contains three columns: - id: A unique identifier that can be usedSegments — Application usage sessions that track when you were using specific applications and windows. Each segment in the segment table includes theEvents — Calendar events and meetings that were scheduled during your computer usage. The event table stores information about these events, including titleYou will need 2 environment variables: REWIND_DB_PATH, REWIND_DB_PASSWORD. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at wordcloud on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. RewindMCP's toolset — Parameters, Returns, Prerequisites and 5 more — is a fair guide to whether it matches your workflow. It is maintained by pedramamini; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Parameters | time_period (required, e.g., '1hour', '30minutes', '1day', '1week'), application (optional, filter by app name) |
| Returns | Frame count per application, OCR node count (activity level), number of unique windows, time range when application was active, sorted by activity level |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Frames | Screenshots captured by Rewind.ai at regular intervals as you use your computer. Each frame in the frame table includes a timestamp (createdAt) and is linked to the application segment it belongs to. Frames are the visua |
| Nodes | Text elements extracted from screen captures using Optical Character Recognition (OCR). Each node in the node table represents a piece of text visible on your screen, including its position (leftX, topY, width, height) a |
| SearchRanking_Content | This table stores the actual OCR text content extracted from screen captures. It contains three columns: - id: A unique identifier that can be used to locate the corresponding recording chunk - c0: The main text content |
| Segments | Application usage sessions that track when you were using specific applications and windows. Each segment in the segment table includes the application bundle ID, window name, start time, and end time. Segments help orga |
| Events | Calendar events and meetings that were scheduled during your computer usage. The event table stores information about these events, including title, start time, end time, and other metadata. Events provide additional con |
{
"mcpServers": {
"rewinddb": {
"command": "python",
"args": ["/path/to/mcp_stdio.py"],
"env": {
"REWIND_DB_PATH": "/path/to/your/rewind.db",
"REWIND_DB_PASSWORD": "your_password"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| REWIND_DB_PATH | Filesystem location the server is allowed to use. | Optional |
| REWIND_DB_PASSWORD | Configuration value read at startup. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.