Backstory imports data exports from services like Google, Telegram, Spotify, and Instagram into a local SQLite database, then lets you search and browse them as one timeline. It also exposes the data over MCP so an AI assistant can query events, entities, and date ranges locally.
From the registry: Search your Google, Telegram, Spotify and Instagram exports locally. Fully offline.
$ dotnet tool install -g Backstory$ backstory model fetchPlease install the `backstory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **.NET 10 SDK** — Install the .NET 10 SDK to run and install Backstory. (https://dotnet.microsoft.com/)
- **Install Backstory as a global .NET tool** — Install the Backstory CLI/server as a global .NET tool. Run: `dotnet tool install -g Backstory`
Optional prerequisites:
- Optional semantic search model — Download the ONNX MiniLM model once to enable higher-quality semantic search. Backstory otherwise uses the default offline hashing embedder. Run: `backstory model fetch`
Canonical MCP server config (stdio transport):
- command: `backstory`
- args: ["serve"]
Note: Backstory runs locally over stdio via `backstory serve`. The database path can be customized with the optional `BACKSTORY_DB` environment variable; if unset, it defaults to `~/.backstory/backstory.db`.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.BACKSTORY_DBPath to the SQLite database file; defaults to ~/.backstory/backstory.db if not set.MCP server for searching Airweave collections with natural language queries.