GET context7.com HTTP 2001.4 s31.5 KB$0.001784 captured Aug 7, 2026

context7.com, as data

One API turns any context7.com page into markdown, structured JSON, its link graph or a screenshot, and crawls the whole site the same way. The panel shows the real response we captured.

target profile from the capture

Render mode: Plain HTTP, no browser needed
Response: HTTP 200 in 1.4 s
Page size: 31.5 KB of markdown, 1,188 lines
Fields: Business Name, Address, Phone, Category and 1 more
Captured: Aug 7, 2026

Start scraping context7.com See the code

Free balance on signup, no card. This context7.com page cost $0.001784 to fetch.

response 200 · 1.4 s · 31.5 KB

Context7 supports all MCP clients. Below are configuration examples for popular clients. If your client isn’t listed, check its documentation for MCP server installation. To configure manually, use the Context7 server URL `https://mcp.context7.com/mcp` with your MCP client and pass your API key via the `Authorization: Bearer YOUR_API_KEY` header.Add this to your Roo Code MCP configuration file. See Roo Code MCP docs for more info.####Add this to your Devin Desktop MCP config file. See Devin Desktop MCP docs for more info.####Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector. Enter the name as `Context7` and the remote MCP server URL as `https://mcp.context7.com/mcp`.####Open Claude Desktop developer settings and edit your `claude_desktop_config.json` file. See Claude Desktop MCP docs for more info.ChatGPT supports MCP servers through remote connectors via Developer Mode (beta). Available for Pro, Plus, Team, Enterprise, and Edu plans.####Go to: `Settings` → `Apps` → `Advanced settings` → Enable `Developer Mode`####Go to: `Settings` → `Apps` → `Create App`Fill in the following:`Fetch up-to-date documentation and code examples for any library directly from the source``https://mcp.context7.com/mcp/oauth`> Accept the security notice and complete the one-time OAuth authorization.Start a new chat → Click the plus icon → Hover over `More` → Select the `Context7` app.Alternatively, you can say `use context7` in your prompt and ChatGPT will automatically use the `Context7` app.See OpenAI MCP docs for more info.The ChatGPT desktop app shares apps configured on the web. Set up the app on chatgpt.com first.####1. Enable Developer Mode (on the Web)Open the ChatGPT desktop app → Start a new chat → ChatGPT will automatically use the `Context7` app when you ask it to.Apps configured on the web are automatically available in the desktop app.See OpenAI MCP docs for more info.

POST /scrape · context7.com/docs/resources/all-clients.md · markdown · Showing 15 of 1,188 lines · captured Aug 7, 2026

What Spider does on context7.com

Same key, five endpoints. The numbers under a cell were measured on this page.

/scrape

Page to markdown

Clean text for RAG and LLM context, boilerplate removed. The lane that runs without a key.

1.4 s · $0.001784

/fetch

Page to JSON

Spider reads the page and names the fields. Pass your own schema when you need exact keys.

/crawl

Whole site

Follows context7.com's own links, respects robots, streams pages as they land.

/links

Link graph

Every internal and external URL on a page, before you decide what to fetch.

/screenshot

Rendered capture

Real Chromium, full-page PNG. The same call also returns the rendered HTML.

The call behind the panel

This request produced the response above. Paste it with your key and you get the same bytes.

request scrape.sh

curl -X POST https://api.spider.cloud/scrape \
  -H "Authorization: Bearer $SPIDER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://context7.com/docs/resources/all-clients", "return_format": "markdown"}'

from spider import Spider

app = Spider()
params = {"return_format": "markdown"}
page = app.scrape_url("https://context7.com/docs/resources/all-clients", params=params)
print(page[0]["content"])

import { Spider } from "@spider-cloud/spider-client";

const app = new Spider();
const [page] = await app.scrapeUrl("https://context7.com/docs/resources/all-clients", {
  return_format: "markdown",
});
console.log(page.content);

plain request · no browser, no selectors

What context7.com costs

Multiplied from the measured 31.5 KB page. Estimates round to the cent.

cost measured

This page, once 31.5 KB over HTTP, measured $0.001784

This page, daily for a month 30 fetches at the measured price ≈ $0.05

1,000 pages this size 30.8 MB at the measured price ≈ $1.78

10,000 pages this size 307.5 MB at the measured price ≈ $17.84

1 GB of transfer costs $1, plus $0.001 per CPU minute, and failed requests cost $0. Crawling daily? The Unlimited plan is a flat monthly rate.

Point this at the rest of context7.com.

The capture above took 1.4 s and cost $0.001784. The same call takes any URL on context7.com.

Get an API key

More in Directories

All Directories scrapers