spidra-mcp-server
Enables AI assistants to scrape pages, batch-process URLs, and crawl entire websites with AI-powered extraction.
README
Spidra MCP Server
The official MCP (Model Context Protocol) server for Spidra — give your AI assistant the ability to scrape pages, batch-process URLs, and crawl entire websites with AI-powered extraction.
Quick start
Get your API key at app.spidra.io under Settings > API Keys.
Claude Code
claude mcp add spidra -e SPIDRA_API_KEY=spd_YOUR_API_KEY -- npx -y spidra-mcp
Cursor / Windsurf / Claude Desktop
{
"mcpServers": {
"spidra": {
"command": "npx",
"args": ["-y", "spidra-mcp"],
"env": {
"SPIDRA_API_KEY": "spd_YOUR_API_KEY"
}
}
}
}
VS Code
{
"mcp": {
"servers": {
"spidra": {
"command": "npx",
"args": ["-y", "spidra-mcp"],
"env": { "SPIDRA_API_KEY": "spd_YOUR_API_KEY" }
}
}
}
}
Tools
Pick by what you want back:
| You want | Use | Waits? |
|---|---|---|
| One combined answer from 1–3 known URLs (multi-URL content is merged; the AI answers once — good for comparing pages) | spidra_scrape |
Yes — returns extracted content directly |
| Separate results per URL, 2–50 known URLs (each processed independently) | spidra_batch_scrape |
No — poll spidra_check_batch_status |
| Data from pages you don't know yet, starting from one URL | spidra_crawl |
No — poll spidra_check_crawl_status |
Full list:
| Tool | Purpose |
|---|---|
spidra_scrape |
Scrape 1–3 URLs with AI extraction, browser actions, proxies, cookies, screenshots. Waits for the result. |
spidra_check_scrape_status |
Check a scrape job if the wait window was exceeded. |
spidra_batch_scrape |
Submit up to 50 URLs with one prompt/schema. Returns a batchId immediately. |
spidra_check_batch_status |
Per-URL statuses and results for a batch. |
spidra_cancel_batch |
Cancel a batch; credits for unprocessed items are refunded. |
spidra_crawl |
Discover and process pages from a starting URL, guided by plain-language instructions. Returns a jobId immediately. |
spidra_check_crawl_status |
Crawl progress, and the extracted data once completed. |
spidra_crawl_pages |
Per-page results with signed HTML/markdown download URLs. |
spidra_crawl_extract |
Re-run a new extraction over a completed crawl without re-crawling. |
spidra_cancel_crawl |
Cancel a crawl; processed pages are kept. |
spidra_scrape_logs |
Browse past jobs and their outputs. |
spidra_usage |
Credit/request/token usage for the account. |
Configuration
| Env var | Required | Description |
|---|---|---|
SPIDRA_API_KEY |
yes | Your Spidra API key (spd_...) |
SPIDRA_API_URL |
no | Override the API base URL (self-hosted / staging) |
HTTP_STREAMABLE_SERVER |
no | true to serve HTTP streamable transport at http://localhost:3000/mcp instead of stdio |
PORT / HOST |
no | HTTP transport bind address (default 3000 / localhost) |
On the HTTP transport, the API key can also be sent per-request via X-Spidra-API-Key or Authorization: Bearer headers.
Credits
Every scraped URL costs credits (base 2 per URL, plus AI tokens; CAPTCHA solves cost 10). The tool descriptions steer the model toward the cheapest tool that answers the question, and cancelling unfinished work refunds unprocessed items.
Development
npm install
npm run build # bundles to dist/index.js
npm test # black-box smoke tests: spawns the built binary against a fake API
npm run typecheck
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.