Search History MCP Server
Enables access to and searching of browser history from major browsers (Brave, Chrome, Firefox, Safari, Edge, Arc, Opera, DuckDuckGo) to personalize LLM interactions and retrieve past browsing data through natural language queries.
README
search-history-mcp
<img width="1024" height="512" alt="browser-histo (2)" src="https://github.com/user-attachments/assets/9bd134ed-b400-45ae-8134-9c3f854989b3" />
Access and search your browser search history (Brave, Chrome, Firefox, Safari, Edge, Arc, Opera, DuckDuckGo) through an MCP server for LLM chat apps.
Supported for MacOS, Windows, and Linux.
https://github.com/user-attachments/assets/19c6de51-8219-453d-9b36-d584c44fbe9f
Use Cases
- Brainstorming: Brainstorm project ideas inspired by your interests and search history.
- LLM Personalization Support: Teach your LLM more about yourself.
- Profile Generation: Build a personal profile based on your search history.
Features
This MCP server provides three tools to interact with your search history:
- search_history: Search for specific terms in URLs and page titles
- get_recent_history: Get the most recent browsing history entries
- get_most_visited: Get your most frequently visited sites
Install
- Install Claude Desktop
- Install uv
- Clone or navigate to this repository
- Setup environment:
uv venv && uv pip install -r pyproject.toml && uv pip install cryptography && source .venv/bin/activate - Install the MCP server:
fastmcp install claude-desktop mcp_server.py - Restart Claude Desktop
Privacy Note
This server reads your local browser history databases in read-only mode. It creates temporary copies to avoid locking issues when browsers are running. For DuckDuckGo on macOS, encryption keys are retrieved from your macOS Keychain and used only to decrypt your local history data. No data is sent anywhere except to your local LLM chat application.
Browser Support: Brave, Chrome, Edge, Opera, Arc, and DuckDuckGo are supported on Windows, macOS, and Linux. Firefox is supported on all platforms. Safari is macOS-only.
Browser file paths may have to be manually configured depending on your file structures.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.