Backstory: Search Your Data Exports Locally MCP Server

Search your Google, Telegram, Spotify and Instagram exports locally. Fully offline.

Local serverstdio

What is the Backstory: Search Your Data Exports Locally MCP server?

Connect Backstory: Search Your Data Exports Locally to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Search your Google, Telegram, Spotify and Instagram exports locally. Fully offline. The backstory: search your data exports locally mcp server is what makes that connection.

What the server does

Search all your data exports in one place. It runs entirely on your own computer, and nothing ever leaves your PC.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • timeline — List events in time order, with the same filters
  • stats — Counts by source and type, and the embedder in use
  • serve — Run the MCP server
  • eval — Run the benchmark
  • search_timeline — Ranked events for a natural-language query
  • get_events — Full event records by id, including a pointer to the source
  • lookup_entity — A person or place by name
  • summarize_period — Every event in a date range, for the agent to summarize
  • list_sources — The sources imported and how many events each has

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

Among the team communication options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Backstory: Search Your Data Exports Locally's toolset — timeline, stats, serve and 6 more — is a fair guide to whether it matches your workflow. It is maintained by magna-nz; 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.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Backstory: Search Your Data Exports Locally.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
timelineList events in time order, with the same filters
statsCounts by source and type, and the embedder in use
serveRun the MCP server
evalRun the benchmark
search_timelineRanked events for a natural-language query
get_eventsFull event records by id, including a pointer to the source
lookup_entityA person or place by name
summarize_periodEvery event in a date range, for the agent to summarize
list_sourcesThe sources imported and how many events each has

How to install the Backstory: Search Your Data Exports Locally MCP server

{
  "mcpServers": {
    "backstory": { "command": "backstory", "args": ["serve"] }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Backstory: Search Your Data Exports Locally to timeline.
  • Use Backstory: Search Your Data Exports Locally to stats.
  • Use Backstory: Search Your Data Exports Locally to serve.

Frequently asked questions

It connects Backstory: Search Your Data Exports Locally to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (timeline, stats, serve, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Backstory: Search Your Data Exports Locally directly.