Deterministic scraping calls
Call importio_page_text or importio_extract_data yourself when you don’t need a model in the loop.
Skip the framework. Open a Streamable HTTP session to Import.io Web Scraper MCP at https://mcp.import.io/mcp and call any Import.io tool from your own code.
import asyncio, os
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async def main():
headers = {"Authorization": f"Bearer {os.environ['IMPORTIO_MCP_KEY']}"}
async with streamablehttp_client("https://mcp.import.io/mcp", headers=headers) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool("importio_page_text",
{"url": "https://example.com", "max_chars": 4000})
print(result.content[0].text)
asyncio.run(main())import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp.js';
const client = new Client({ name: 'my-app', version: '1.0.0' });
await client.connect(new StreamableHTTPClientTransport(new URL('https://mcp.import.io/mcp'), {
requestInit: { headers: { Authorization: `Bearer ${process.env.IMPORTIO_MCP_KEY}` } },
}));
const res = await client.callTool({
name: 'importio_page_text',
arguments: { url: 'https://example.com', max_chars: 4000 },
});
console.log(res.content);Any public page, rendered, through managed proxies
Rendering, proxy routing, captcha handling, extraction
https://mcp.import.io/mcp
Call Import.io tools directly from the official Python and TypeScript SDKs.
Call importio_page_text or importio_extract_data yourself when you don’t need a model in the loop.
Embed Import.io in a product that already speaks MCP.
Inspect exact inputs and outputs before wiring tools into an agent.
pip install mcp, or npm install @modelcontextprotocol/sdk.https://mcp.import.io/mcp with a bearer header.You don’t need one. The server speaks standard MCP, so the official SDKs, and every framework built on them, work unchanged.
Signup includes 10,000 successful calls. After that it is $0.0002 per successful call. Setup requests, tool listings, malformed requests, blocked requests and failed upstream calls are never billed, and you can set a monthly spend limit that stops paid usage when reached.
Use OAuth in interactive clients that support it: the client opens a sign-in, stores the credentials and reuses them. Use an API key for scripts, servers and clients without OAuth, sent as Authorization: Bearer mcp_live_…. Keep keys out of prompts and shared config files.
importio_web_fetch, importio_render, importio_extract_data and importio_get_html, page helpers such as importio_page_text, importio_page_links and importio_search_cards, and browser actions for clicks, form input, scrolling, pagination, waits, screenshots and captcha handling. Requests can pick a proxy country and type, with bounded retries when a page blocks.
Pass one server in mcp_servers and Claude calls Import.io tools server-side.
Setup 5 minMCPImport.io tools in generateText and streamText for TypeScript apps.
Setup 10 minMCPImport.io as a Streamable HTTP MCP server for your agents.
Setup 10 minMCPOffer Import.io web data tools inside your own agent platform with OAuth.
Setup 1 day