thunderbit-web-scraping-mcp
OfficialThunderbit MCP Server
Open-source toolkit for the Thunderbit Open API — CLI, MCP server, and Claude Code plugin.
This monorepo ships three packages, all backed by the Thunderbit Open API:
Package | Purpose | Audience |
Command-line tool for distill / extract / batch | Developers, scripts, CI | |
Model Context Protocol server (7 tools) | AI assistants — Claude Desktop, Cursor, Cline, Claude Code | |
Bundled MCP + 4 skills | Claude Code users |
Get a free API key at app.thunderbit.com/console/api-keys.
Quick Start
CLI
npm i -g @thunderbit/thunderbit-cli
export THUNDERBIT_API_KEY=tb_your_api_key_here
thunderbit distill https://example.com -f markdownMCP Server (Claude Desktop / Cursor / Cline)
Edit your MCP client config:
{
"mcpServers": {
"thunderbit": {
"command": "npx",
"args": ["-y", "@thunderbit/mcp-server"],
"env": { "THUNDERBIT_API_KEY": "tb_your_api_key_here" }
}
}
}Claude Code Plugin
claude plugin marketplace add thunderbit-com/thunderbit-mcp-server
claude plugin add thunderbit
export THUNDERBIT_API_KEY=tb_your_api_key_hereRelated MCP server: Anybrowse
What you can do
Convert any web page into clean, LLM-ready Markdown
Extract structured data from pages using JSON Schema
Get AI-suggested fields when you don't know what's on a page
Run batch jobs on up to 100 URLs at a time
Pricing
Distill — 1 credit. Extract — 20 credits. Suggest fields — free. Batch jobs scale per URL. Status polling is free.
Top up at app.thunderbit.com/console/billing.
Development
git clone https://github.com/thunderbit-com/thunderbit-mcp-server.git
cd thunderbit-mcp-server
# each package is independent
cd packages/mcp-server && npm install
cd packages/cli && npm installAPI Reference
The full HTTP contract is documented in openapi.yaml (OpenAPI 3.1) — base URL https://openapi.thunderbit.com, Bearer auth with your THUNDERBIT_API_KEY.
License
MIT © Thunderbit
This server cannot be deployed
Maintenance
Related MCP Connectors
Scrape, crawl and search the web for AI agents via MCP.
Web scraping for AI agents. Extract text and metadata from any URL worldwide. $0.005/page.
- mcpOAuthcom.sequentum
Turn the web into structured, reliable, actionable enterprise data for AI Agents
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI models to scrape and extract data from any website globally using Thordata's 195+ country proxy network. Bypasses anti-bot systems and renders JavaScript content, outputting structured data in Markdown, HTML, or Links format.MIT
- AlicenseAqualityDmaintenanceMCP-native web scraping and search API for AI agents. Converts any URL to clean Markdown with 90% success rate, including Cloudflare-protected sites and JS SPAs. Real-time web search via Brave Search API. CAPTCHA solving built-in. 10 free scrapes/day.51 npm5MIT
- AlicenseNot gradedqualityBmaintenanceThe web data platform for AI agents. Fetch, search, crawl, extract, monitor, and screenshot any URL. 55+ domain extractors, 65-98% token savings. 7 MCP tools included.332 npm12AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceMCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.41MIT