Massive
About
Real-time web access for AI agents — fetch any URL, search Google, and query AI chatbots with JS rendering, captcha solving, and 195+ country geo-targeting.
Details
- Author
- joinmassive
- Categories
- Web Scraping, Search, Knowledge Base
Jump to
Setup
Install Massive in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/joinmassive/mcp-server
Follow the installation instructions in the repository README, then restart your MCP client.
Official MCP server for theMassive Web Render API. Give your AI agents real-time web access — fetch any URL, search Google, query AI chatbots — with JS rendering, captcha solving, and 195+ country geo-targeting handled automatically.
- Download the latestmassive-mcp-X.Y.Z.mcpbfrom GitHub Releases.
- Open the file with Claude Desktop (or drag-drop into Settings → Extensions).
- Paste your Massive API token when prompted. Token is stored in your OS keychain.
Add to~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or%APPDATA%\Claude\claude_desktop_config.json(Windows):
{ "mcpServers": { "massive": { "command": "npx", "args": ["-y", "@joinmassive/mcp-server"], "env": { "MASSIVE_TOKEN": "your-token-here" } } } }
One command, works across all your projects:
claude mcp add massive --scope user -e MASSIVE_TOKEN=your-token-here -- npx -y @joinmassive/mcp-server
Then/mcpin any Claude Code session to confirm it's connected. Drop--scope userto scope it to the current project only.
The same JSON snippet works for any MCP-compatible client. Drop it into the client's config file:
Ifnpxisn't on the client's PATH, swap to a direct binary path:"command": "node", "args": ["/absolute/path/to/dist/index.js"].
Fetch any URL. Returns Markdown by default (best for LLMs).
Example prompt:"Use the Massive MCP server to fetchhttps://news.ycombinator.comand summarise the top stories."
Google search results, parsed into structured JSON.
Returns:{ organic, ai_overview, people_also_ask, query }.
{ "query": "best espresso machines 2026", "organic": [ { "title": "...", "url": "https://...", "snippet": "..." } ], "ai_overview": { "answer": "...", "sources": [{ "domain": "wirecutter.com", "url": "https://..." }] }, "people_also_ask": [ { "question": "What is the best espresso machine for beginners?", "answer": "" } ] }
Example prompt:"Use web_search to find recent reviews of espresso machines and return the top 3 organic results plus the AI overview."
Returns:{ completion, sources, model, subqueries? }.
No args. Returns{ credits_remaining }. Useful to warn the user before they run out of credits. Free — does not consume credits.
Credit costs (live reference:https://joinmassive.com/pricing):
Worked example:web_fetchwithdifficulty=mediumcosts1 × 2 = 2 credits.
- Cache:expiration(days) reuses recent results. Default1. Setexpiration=0only when freshness matters (prices, scores, weather).
- Difficulty:start with defaultlow. Bump tomedium/highonly if the low attempt fails.
- Check first:callaccount_status(free) before launching a batch.
This server exposes three read-only reference documents atdocs://URIs. They show up in your MCP client as attachable references:
In Claude Desktop: open the Connectors panel and pick the resource from this server. In Claude Code: type@and search by name.The model does not auto-read these — they're for you to browse.
"MASSIVE_TOKEN env var is not set"Confirm theenvblock in your Claude Desktop config has the token. Restart Claude Desktop.
"Massive endpoint is autoscaling, please retry"A 503 from upstream. The server already retried once; wait ~10s and try again.
"403 Forbidden — the request was rejected (likely captcha or invalid token)"Either the target site rejected our captcha solver, or the token is invalid. Re-check the token at the dashboard.
No tools appear in Claude DesktopSettings → Developer → check the MCP server logs. The most common cause iscommand: "npx"not being on Claude Desktop's PATH. Runwhich npxin Terminal — if it's under Homebrew (/opt/homebrew/bin), Claude Desktop's PATH won't include it. As a workaround, use a direct path:"command": "node", "args": ["/absolute/path/to/dist/index.js"]. Or install the.mcpbbundle (Option A above), which sidesteps PATH issues entirely.
Issues and PRs welcome atgithub.com/joinmassive/mcp-server.
Official OpenWeb Ninja MCP server connecting any AI agent to 40+ web data APIs for web search, e-commerce, local business, jobs, real estate, and finance data.
Search and retrieve rental property details from Daft.ie via web scraping.
Crawl websites to generate Markdown documentation and make it searchable through an MCP server.
Extracts document content from Microsoft Learn and GitHub URLs and stores it in PocketBase for retrieval and search.
An MCP server that routes search queries through public SearXNG instances. Instead of paying per query to SerpAPI, Exa, or Brave Search, this server fans out to multiple public SearXNG instances simultaneously, merges the results, and returns the best ones.
Give your AI agent live Google Maps search, review, and photo data through one secure MCP connection.
AI Influencer Search, Creator Data, & Live Scraping
Discovers and collects MCP servers from the internet.
MCP Server for Stealth Web Search and Fetching
Fault-tolerant MCP Server for Stealth Web Search and Fetching
MCP Server for Scrape.do - Web Scraping & Google Search with anti-bot bypass
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
