Happy slice of mcp pizzaMCP.pizza

hister

MCP.Pizza Chef: asciimoo

Hister runs quietly on your own computer, keeping a full-text, searchable record of the web pages you visit and the local files you choose to include. Once installed, you can search that private archive from a web page, a terminal window, or an AI assistant connected through MCP, so you can ask your assistant to find a page you read last week or a document buried in your files. It works entirely on infrastructure you control, with no required account or cloud service, though setup does involve downloading a small program and adding a browser extension.

Data
Files/PDF
Web/Research

Use This MCP server To

Find a webpage I visited last month by its content Search my personal files and browsing history from one place Ask my AI assistant to pull up a page I read before Search from the terminal instead of digging through browser tabs Keep my search history private with no cloud account needed Find documents by their meaning, not just exact wording Import my existing browser history so it's all searchable at once

README

Hister

Your own search engine

Hister is a private search engine for the pages you visit and the files you keep. It indexes their full contents so you can find information again from the web interface, terminal, or an AI assistant connected through MCP.

Try the demo · Download Hister · Read the quickstart · Documentation

Hister web interface

Quickstart

  1. Download the binary for your platform from the latest release, then rename it to hister (hister.exe on Windows).

  2. On Linux or macOS, make it executable:

    chmod +x hister

  3. Start Hister on Linux or macOS:

    ./hister listen

    On Windows, run .\hister.exe listen in PowerShell.

  4. Open http://127.0.0.1:4433 and install the browser extension for Firefox or Chrome.

No configuration is required for a local personal setup. See the complete quickstart to import existing browser history and choose what Hister indexes.

Features

  • Privacy focused: No telemetry or mandatory cloud service. Run Hister locally or on infrastructure you control.
  • Full text indexing: Search the actual contents of visited pages and local files, not only titles and URLs.
  • Automatic browser indexing: Save newly visited pages with the Firefox or Chrome extension.
  • Powerful queries: Use field filters, phrases, wildcards, negation, aliases, and result priorities.
  • Optional semantic search: Find documents by meaning through an embeddings endpoint you configure.
  • Crawler and browser import: Index websites or bring in existing browser history.
  • Web, terminal, and MCP clients: Search from the browser, TUI, command line, or an AI assistant.
  • Multi user support: Keep each user's documents and search results separate on a shared server.

Hister terminal interface

Privacy

By default, Hister has no telemetry and no cloud sync. The browser extension sends indexed page content only to the Hister server you configure, apart from downloading page favicons. The server stores documents and search indexes on that server.

hister FAQ

Can I use this to find a webpage I visited weeks ago?
Yes — Hister keeps a full-text record of pages you have visited, so you can search for words or phrases from the page itself, not just its title or web address.
Can I use this to search my own documents alongside my browsing history?
Yes — you can choose to have Hister index local files as well as visited pages, so both show up together in the same search.
Which AI assistants can this connect to?
Hister exposes its search through MCP, so it can be connected to assistants such as Claude, ChatGPT, or other MCP-compatible tools, in addition to its own web and terminal search.
Do I need to create an account or sign up for a service?
No — Hister runs on your own computer or server, and no account or cloud sign-up is required for a personal setup.
Do I need an API key to use it?
No API key is required to run Hister itself; a key is only needed if you turn on the optional feature that searches by meaning instead of exact words.
How hard is it to set up?
You download a single program for your computer, run it, and add a browser extension so it starts saving pages automatically — no coding is required, though it takes a few more steps than a one-click install.
Is my data kept private?
Yes — by default nothing is sent to any outside company; your indexed pages and files stay on the server you run, and any remote features are optional and off by default.
Can more than one person use the same Hister setup?
Yes — Hister supports multiple users on a shared server while keeping each person's documents and search results separate.