PluginBench
MCP Server
Maintained
MIT

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

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

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

RepositoryRegistry
How to choose

What this kind of tool is for

  • Scaffold, lint, or restyle a component your agent is already editing.
  • Run accessibility, link, or screenshot checks against a local build.
  • Turn a design constraint into generated markup the agent can iterate on.

How to compare servers like this

Framework fit:
Check the tool targets your stack (React, Vue, plain HTML) before installing it.
Runtime needs:
Some browser-driving tools need a local browser or display; read the setup notes first.
Maintenance signal:
Frontend tooling churns quickly; recent commits are a good filter.
Output quality:
Prefer tools whose generated code you would accept into the repo as-is.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

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

The Thunderbit MCP server is an AI-powered web scraping tool that converts web pages into Markdown format 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, allowing you to distill web pages into clean Markdown or extract structured data according to JSON Schema specifications. It's useful for content aggregation, data extraction, and feeding web information into AI pipelines.

How to install io.github.thunderbit-open/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
JSON config
{
  "mcpServers": {
    "thunderbit-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@thunderbit/mcp-server"
      ],
      "env": {
        "THUNDERBIT_API_KEY": "<YOUR_THUNDERBIT_API_KEY>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Web page to Markdown conversion — Convert web pages into clean, readable Markdown format
  • JSON Schema-based data extraction — Extract structured data from web pages using JSON Schema definitions

Use cases

  • Extract structured data from websites using JSON Schema definitions
  • Convert web pages to Markdown for AI processing and analysis
  • Aggregate content from multiple web sources into a unified format
  • Automate data collection workflows for research or business intelligence
  • Feed web content into AI pipelines for further processing

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

What is the Thunderbit MCP server?

It's an AI-powered web scraping tool that distills web pages to Markdown or extracts structured data via JSON Schema, designed for integration with AI agents.

Is it free to use?

The README does not specify pricing; check the GitHub repository for licensing details.

How do I install it?

Install via npm with: npm install @thunderbit/mcp-server, then configure it in your MCP client (Cursor, Claude, etc.).

What authentication is required?

The README does not specify authentication requirements; refer to the GitHub repository for setup details.

Can I use it for any website?

Yes, it can scrape and extract data from web pages, though you should respect robots.txt and terms of service.

What output formats does it support?

It supports Markdown output for page distillation and JSON output for structured data extraction via JSON Schema.

Related MCP servers

Draw and visually collaborate with AI agents on tldraw's infinite canvas.

50k
TypeScript
View repository →

Generate styled PNG/SVG map images of any location with 11 customizable color themes.

0
Python
MIT
View repository →
MEmelta UI logo

melta UI

Active

AI-ready design system MCP: enforce design contracts with tokens, rules, and automated HTML verification.

195
TypeScript
MIT
View repository →

Local Figma plugin integration with 60 tools for live read/write access—no API token or rate limits.

8
Go
MIT
View repository →

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

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

0
TypeScript
View repository →