MCP Server

Maintained

MIT

io.github.thunderbit-com/thunderbit-mcp-server MCP Server

io.github.thunderbit-com/thunderbit-mcp-server

AI-powered web scraping with Markdown conversion and structured JSON Schema extraction.

What is the io.github.thunderbit-com/thunderbit-mcp-server MCP server?

The Thunderbit MCP server is an AI-powered web scraping tool that converts web pages to Markdown or extracts structured data using JSON Schema. It enables AI agents to efficiently gather and transform web content for analysis and integration.

This server provides web scraping capabilities optimized for AI workflows. It can distill web pages into clean Markdown format or extract specific structured data by defining a JSON Schema, making it useful for content aggregation, data extraction, and web intelligence tasks.

How to install io.github.thunderbit-com/thunderbit-mcp-server

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

THUNDERBIT_API_KEY
required
secret
Your Thunderbit API key (tb_...). Get one at https://app.thunderbit.com/console

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "thunderbit-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@thunderbit/mcp-server"
      ],
      "env": {
        "THUNDERBIT_API_KEY": "<YOUR_THUNDERBIT_API_KEY>"
      }
    }
  }
}

Use cases

Extract product information from e-commerce sites into structured JSON format
Convert web articles and documentation to Markdown for processing by language models
Scrape multiple pages and consolidate data into a unified schema
Gather competitive intelligence by extracting specific fields from competitor websites
Automate content collection for knowledge bases or research projects

io.github.thunderbit-com/thunderbit-mcp-server MCP server FAQ

What does the Thunderbit MCP server do?

It provides AI-powered web scraping with two main capabilities: converting web pages to clean Markdown format, or extracting structured data by defining a JSON Schema for the content you want to capture.

Is this server free to use?

The README does not specify pricing or licensing details. Check the GitHub repository or Thunderbit's website for current terms.

How do I install it?

Install via npm using the package @thunderbit/mcp-server, then configure it in your MCP client (Cursor, Claude, or other compatible tools).

What authentication is required?

The README does not document authentication requirements. Refer to the GitHub repository for setup and credential details.

Can I use this for any website?

The server is designed for general web scraping, but always respect website terms of service and robots.txt policies when scraping.

What format does it output?

It outputs either Markdown (for page distillation) or structured JSON data (when you provide a JSON Schema to define the extraction pattern).

Related MCP servers

io.github.thunderbit-open/thunderbit-mcp-server

Maintained

AI-powered web scraping with Markdown distillation and JSON Schema extraction.

JavaScript

MIT

View repository →

ThunderPhone

Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns.

io.github.thuupx/lunge

Active

Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections

TypeScript

View repository →

io.github.thuupx/memory-mcp-lite

Maintained

A lightweight, structured, token-efficient local-first MCP memory server

TypeScript

View repository →

Algenta MCP Server

Active

Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.

TypeScript

Apache-2.0

View repository →

Codna — repository intelligence

Repo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.

View repository →