Decipher Research Agent

v1.0.0Coding Agentsstable

Turn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.

agentagentic-aiaiartificial-intelligencecrewai
Share:
151
Stars
0
Downloads
0
Weekly
0/5

What is Decipher Research Agent?

Decipher Research Agent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to turn topics, links, and files into ai-generated research notebooks — summarize, explore, and ask anything.

Turn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Turn topics, links, and files into AI-generated research not

Use Cases

Generate AI research notebooks from topics
Summarize links and uploaded documents
Explore and ask questions about research
mtwn105

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 8, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx decipher-research-agent

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Decipher Research Agent

Decipher Research Agent (DecipherIt) is a full-stack AI research platform that transforms topics, URLs, and uploaded documents into structured research notebooks. It uses a CrewAI multi-agent pipeline — with specialized agents for web scraping, analysis, content writing, FAQ generation, and mindmap creation — backed by Bright Data for web content extraction and Qdrant for vector search. Researchers and content creators use it to synthesize multi-source research into summaries, FAQs, hierarchical mindmaps, and even podcast-style audio overviews in a single automated workflow.

Prerequisites

  • Node.js 18+ and pnpm for the Next.js frontend
  • Python 3.10+ and uv for the FastAPI backend
  • API keys: OpenAI or OpenRouter (LLM), Bright Data (web scraping), Qdrant (vector DB), Cloudflare R2 (file storage)
  • A PostgreSQL database for the frontend (SQLite via Prisma for development)
  • An MCP-compatible client such as Claude Desktop if using the MCP server mode
1

Clone the repository

Clone the decipher-research-agent monorepo and enter the project directory.

git clone https://github.com/mtwn105/decipher-research-agent.git
cd decipher-research-agent
2

Set up the frontend

Install frontend dependencies, copy the environment template, generate Prisma types, and run database migrations.

cd client
pnpm install
cp .env.example .env.local
pnpm prisma generate
pnpm prisma migrate dev
3

Configure frontend environment variables

Edit `client/.env.local` with your database URL, auth secret, and Cloudflare R2 storage credentials.

DATABASE_URL=postgresql://user:pass@localhost:5432/decipher
BETTER_AUTH_SECRET=your-random-secret
BETTER_AUTH_URL=http://localhost:3000
R2_ENDPOINT=https://your-account.r2.cloudflarestorage.com
R2_ACCESS_KEY_ID=your-r2-access-key
R2_SECRET_ACCESS_KEY=your-r2-secret-key
R2_BUCKET_NAME=your-bucket
R2_PUBLIC_URL=https://your-r2-public-url
NEXT_PUBLIC_BASE_URL=http://localhost:3000
4

Set up the backend

Create a Python virtual environment with uv, install dependencies, and copy the backend environment template.

cd ../backend
uv venv
source .venv/bin/activate
uv sync
cp .env.example .env
5

Configure backend environment variables

Edit `backend/.env` with your LLM, Bright Data, Qdrant, and Cloudflare credentials.

OPENAI_API_KEY=sk-your-openai-key
OPENROUTER_API_KEY=your-openrouter-key
LEMONFOX_API_KEY=your-lemonfox-key
BRIGHT_DATA_API_TOKEN=your-bright-data-token
BRIGHT_DATA_WEB_UNLOCKER_ZONE=your-zone-name
QDRANT_API_URL=https://your-qdrant-cluster-url
QDRANT_API_KEY=your-qdrant-key
CLOUDFLARE_ACCOUNT_ID=your-account-id
CLOUDFLARE_R2_ACCESS_KEY_ID=your-r2-key
CLOUDFLARE_R2_SECRET_ACCESS_KEY=your-r2-secret
6

Start both servers

Run the frontend and backend development servers in separate terminals.

# Terminal 1 - Frontend
cd client && pnpm dev

# Terminal 2 - Backend
cd backend && uv run uvicorn server:app --host 0.0.0.0 --port 8001

Decipher Research Agent Examples

Client configuration

If exposing the backend as an MCP server endpoint, connect Claude Desktop to the local FastAPI server.

{
  "mcpServers": {
    "decipher-research-agent": {
      "url": "http://localhost:8001/mcp"
    }
  }
}

Prompts to try

Use the web interface at http://localhost:3000 or the MCP connection to run research tasks.

- "Research the latest advancements in CRISPR gene editing and generate a summary with key findings."
- "Summarize this URL and extract the main arguments: https://example.com/article"
- "Create a research notebook on quantum computing applications in cryptography."
- "Generate a FAQ from this uploaded PDF: [attach file]"
- "Build a mindmap of the major topics in machine learning interpretability."

Troubleshooting Decipher Research Agent

Backend fails to start with 'ModuleNotFoundError'

Ensure you ran `uv sync` inside the `backend/` directory with the virtual environment activated (`source .venv/bin/activate`). The backend dependencies are managed separately from the frontend.

Web scraping agents fail or return empty content

Verify your BRIGHT_DATA_API_TOKEN is valid and BRIGHT_DATA_WEB_UNLOCKER_ZONE matches an active zone in your Bright Data account. Check your Bright Data dashboard to confirm the zone is active and has remaining traffic credits.

Prisma migration fails during frontend setup

Confirm DATABASE_URL in `client/.env.local` points to a running PostgreSQL instance. For quick local development, you can use SQLite by changing the provider in `prisma/schema.prisma` to `sqlite` and updating DATABASE_URL to `file:./dev.db`.

Frequently Asked Questions about Decipher Research Agent

What is Decipher Research Agent?

Decipher Research Agent is a Model Context Protocol (MCP) server that turn topics, links, and files into ai-generated research notebooks — summarize, explore, and ask anything. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Decipher Research Agent?

Follow the installation instructions on the Decipher Research Agent GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Decipher Research Agent?

Decipher Research Agent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Decipher Research Agent free to use?

Yes, Decipher Research Agent is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "decipher-research-agent": { "command": "npx", "args": ["-y", "decipher-research-agent"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Decipher Research Agent?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides