Thunderbit MCP server
io.github.thunderbit-com/thunderbit-mcp-server·v1.0.4AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.
58 downloads/wk
Reviews
Write oneNobody has reviewed Thunderbit yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Thunderbit tools (7, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
thunderbit_batch_distill_createwrite actionCreate a batch job to distill multiple URLs into Markdown (max 100 URLs). Returns a job ID — poll thunderbit_batch_distill_status until complete. Costs 1 credit per URL.
thunderbit_batch_distill_statusPoll the status and retrieve results of a batch distill job. Free (0 credits).
thunderbit_batch_extract_createwrite actionCreate a batch job to extract structured data from multiple URLs (max 100 URLs). Returns a job ID — poll thunderbit_batch_extract_status until complete. Costs 20 credits per URL.
thunderbit_batch_extract_statusPoll the status and retrieve results of a batch extract job. Free (0 credits).
thunderbit_distillConvert a web page into clean, LLM-ready Markdown. Ideal for research, content analysis, RAG ingestion, and reading articles behind complex layouts. Costs 1 credit per call.
thunderbit_extractExtract structured data from a web page using a JSON Schema. Perfect for lead generation, price monitoring, competitive analysis, and dataset building. Use thunderbit_suggest_fields first if you don't know the page structure. Costs 20 credits per call.
thunderbit_suggest_fieldsAnalyze a web page and automatically suggest extractable fields/columns. Start here when you don't know what data a page contains — returns field names, types, and extraction instructions usable directly with thunderbit_extract. Free — no credits consumed.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan5 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
How Thunderbit compares
Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 55/100
- higher than 10% of 866 Scraping and browsing servers
- Tools
- 7
- the typical Scraping and browsing server has 6
- Tools that change things
- 29%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 58
- more than 40% of 309 Scraping and browsing servers with a package
What its tools let an agent do: 5 read · 2 change
Install Thunderbit in Claude Code, Cursor or VS Code
Runs npx -y @thunderbit/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add thunderbit-mcp-server -- npx -y @thunderbit/mcp-server
Thunderbit: common questions
- Is Thunderbit MCP server safe?
- With care: it is graded C, so read the findings first (55/100). Read the Thunderbit safety report
- How do I install Thunderbit?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Thunderbit need an API key?
- Yes. The registry entry asks for
THUNDERBIT_API_KEY. - Is Thunderbit maintained?
- The latest release is v1.0.4.
- What can I use instead of Thunderbit?
- Servers from other publishers that do the same job: Talonic MCP server, MCP server and Open Agent Search MCP server.
- How does Thunderbit compare with other Scraping and browsing MCP servers?
- safety score 55/100 (higher than 10% of 866 Scraping and browsing servers); tools 7 (the typical Scraping and browsing server has 6); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Thunderbit
Same job from other publishers: the closest match first, then the best rated.
- TalonicExtract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.not reviewedGrowingA
- MCPScrape any website, extract structured data, and collect web content at scale with AI agentsnot reviewedGrowingA
- Open Agent SearchSearch the web, news, images, videos and books, and extract page content for AI agents.not reviewedGrowingA
- MistralMistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.not reviewedGrowingB
- Rendex: Rendering API for Images, PDFs & Content ExtractionRender HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.not reviewedGrowingA