Deep-research

Created By
ssdeanxa year ago
MCP Deep Research Server using Gemini creating a Research AI Agent
Overview

what is Open Deep Research?

Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and Gemini large language models. It is designed to refine research direction over time and provide comprehensive insights.

how to use Open Deep Research?

To use Open Deep Research, you can either integrate it as a Model Context Protocol (MCP) tool for AI agents or run it standalone via the command line interface (CLI). You need to set up the environment variables and install the necessary dependencies before starting the server.

key features of Open Deep Research?

  • MCP Integration for seamless AI agent usage
  • Iterative research capabilities
  • Intelligent query generation using Gemini LLMs
  • Configurable depth and breadth parameters for research
  • Smart follow-up question generation
  • Comprehensive markdown report generation
  • Concurrent processing of multiple searches

use cases of Open Deep Research?

  1. Conducting in-depth research on emerging technologies
  2. Generating detailed reports for academic papers
  3. Assisting AI agents in gathering information on specific topics

FAQ from Open Deep Research?

  • What is the purpose of Open Deep Research?

It aims to provide a simple implementation of a deep research agent that can refine its research direction over time.

  • What are the requirements to run Open Deep Research?

You need a Node.js environment and API keys for Firecrawl and Gemini.

  • Can I use Open Deep Research without MCP?

Yes, it can be used standalone via the CLI.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
ssdeanx
Star
8
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago