Web3 Research

Deep Research for crypto - free & fully local

typescript

153

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "aaronjmars-web3-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "web3-research-mcp@latest"
      ]
    }
  }
}

Web3 Research MCP is an MCP server that lets you run local, self-contained crypto research workflows. It coordinates multi-source lookups, structured reporting, and progress tracking for token research, all running in your environment to keep data private and under your control.

How to use

Install and run the MCP server locally, then connect to it from your MCP client. You will create a research plan for a token, run searches across multiple sources, save resources, update progress, and generate a final report that covers fundamentals, market data, and sentiment.

How to install

Prerequisites: Node.js v16 or higher must be installed on your system.

Install the MCP server client for your MCP client (Claude Desktop example shown). Run this command to install the Web3 Research MCP client for Claude Desktop via Smithery:

npx -y @smithery/cli install web3-research-mcp --client claude

Using with Claude Desktop

Configure Claude Desktop to load the MCP server by adding a server entry to your Claude Desktop config.

{
  "mcpServers": {
    "web3-research-mcp": {
      "command": "npx",
      "args": ["-y", "web3-research-mcp@latest"]
    }
  }
}

Available tools

create-research-plan

Creates a structured research plan for a token using the token name and ticker.

search

Performs a web search and returns results across web sources.

research-with-keywords

Searches for a token with specific keywords and saves the results for reference.

update-status

Updates the status of a research section (planned, in_progress, completed).

fetch-content

Fetches content from a URL and saves it as a resource in your library.

list-resources

Lists all saved resources that have been collected during research.

search-source

Searches for token information from a specific source (e.g., CoinGecko, DeFiLlama, News).