Advertise
MCP.so
Sign In

DeepRe - AI駆動の深い調査レポート生成ツール MCP Server

@hirokidaichi

Repository

Basic information

Category

Other

License

MIT

Transports

stdio

Author

hirokidaichi

About DeepRe - AI駆動の深い調査レポート生成ツール MCP Server

local mcp server perplexity

DeepRe - AI駆動の深い調査レポート生成ツール MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "deepre": {
      "command": "deno",
      "args": [
        "task",
        "install"
      ]
    }
  }
}

DeepRe - AI駆動の深い調査レポート生成ツール MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is DeepRe - AI駆動の深い調査レポート生成ツール?

DeepRe - AI駆動の深い調査レポート生成ツール is a Deno-based CLI tool that automatically generates in-depth research reports on a specified theme. It leverages the Google Gemini AI API to iteratively collect and evaluate information until sufficient quality is reached, then produces a comprehensive report in Markdown format. The tool is designed for users who need systematic, automated research on any topic, with full Japanese language support.

How to use DeepRe - AI駆動の深い調査レポート生成ツール?

Install globally with deno task install, then run deepre "調査テーマ". Optionally specify an API key with -k, output directory with -o (default ./research), Gemini model with -m (default gemini-2.0-flash), and iteration count with -i (default 10). The API key can also be set via the GEMINI_API_KEY environment variable. Development tasks include deno task deepre for running in dev mode and deno task check-all for linting, type checking, formatting, and tests.

Key features of DeepRe - AI駆動の深い調査レポート生成ツール

  • Iterative research process with automatic quality evaluation
  • Integrates with Gemini 2.0 AI models for advanced search and analysis
  • Automatically generates an optimal research plan from a theme
  • Full Japanese language support for themes and output
  • Produces formatted Markdown reports

Use cases of DeepRe - AI駆動の深い調査レポート生成ツール

  • Preliminary research for academic projects
  • Market trend and competitive analysis
  • Technology trend investigation
  • In-depth information gathering on specific topics

Frequently asked questions

1

What runtime and API key are required?

Deno runtime is required, along with a Google Gemini API key. The key can be passed via the `GEMINI_API_KEY` environment variable or the `-k` command-line option.

2

What is the default model and iteration count?

The default Gemini model is `gemini-2.0-flash` and the default iteration count is 10. You can override both with the `-m` and `-i` flags respectively.

3

What output format does DeepRe produce?

Reports are output as formatted Markdown files. The default output directory is `./research`, configurable with the `-o` flag.

4

Does DeepRe support Japanese?

Yes, it fully supports Japanese for both setting themes and generating output. The README and usage examples are also in Japanese.

Comments

More Other MCP servers

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Advertise