More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Cloudflare Web Search MCP

    1

    Deep web research, supplier sourcing, and doc extraction with zero API billing. Compatible with Claude Code, Cursor, Copilot & 20+ agents.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Cloudflare Web Search MCP

    Cloudflare Web Search MCP

    Example session with this skill installed

    Find the latest migration guide for upgrading from Next.js 14 to 15, specifically regarding the new caching defaults and async request APIs.

    • Read your context and instructions
    • Compiled the cloudflare web search

    I have searched for the official Next.js 15 migration documentation and extracted the specific changes regarding caching and asynchronous request APIs.

    Next.js 15 Migration Analysis

    FeatureChange TypeDescription
    Request APIsBreakingcookies, headers, params, and searchParams are now asynchronous.
    Data CachingDefault Changefetch requests are no longer cached by default (no-store is now the default).
    Client Router CacheDefault ChangestaleTime for Page components is now 0 seconds by default.
    Link ComponentOptimizationPrefetching now defaults to null, meaning it only prefetches the loading state.

    Implementation Detail: Async Request APIs

    You must now await cookies() and headers(). In versions prior to 15, these were synchronous.

    // Before (Next.js 14)
import { cookies } from 'next/headers';
const cookieStore = cookies();
const token = cookieStore.get('token');

// After (Next.js 15)
import { cookies } from 'next/headers';
async function MyComponent() {
  const cookieStore = await cookies();
  const token = cookieStore.get('token');
}

    Data Caching Migration

    To opt back into the old behavior where fetches were cached by default, you must explicitly set the cache option:
    fetch(url, { cache: 'force-cache' })

    Next steps

    1. Update your middleware to handle async cookie access if applicable.
    2. Review your fetch calls and add cache: 'force-cache' to endpoints that require static generation.
    3. Run the official codemod: npx @next/codemod@canary upgrade next@15

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Traditional search APIs are expensive and often miss the technical depth required for software engineering. This skill enables autonomous research, documentation lookup, and supplier discovery without consuming paid API credits by utilizing a free metasearch stack.

    What it does

    • Multi-angle search executes up to six concurrent queries to capture diverse viewpoints on complex topics.
    • Deep page extraction fetches full text from target URLs with SSRF protection to bypass snippet limitations.
    • Specialized modes optimize results for technical documentation, global news, commercial products, or industrial suppliers.
    • GitHub discovery searches repositories, issues, and code directly via the GitHub API.
    • Market targeting localizes searches for specific regions including Saudi Arabia, UAE, and China for sourcing hardware or manufacturing.

    How it works

    1. The agent decomposes your request into targeted search terms and selects the appropriate mode.
    2. It executes a search or multi_search across a free stack including SearXNG, DuckDuckGo, and Bing.
    3. High-relevance URLs are processed via fetch_page to read actual documentation or articles.
    4. The agent synthesizes the findings, providing specific citations and canonical links for all data.

    Frameworks & tools

    Built for the Model Context Protocol (MCP), this skill integrates with Claude Code, Cursor, GitHub Copilot, and Windsurf. It runs via a local Node.js stdio process or as a remote Cloudflare Worker using SearXNG, DuckDuckGo, and the GitHub API.

    Why this beats prompting it yourself

    Standard LLMs suffer from knowledge cutoffs and often hallucinate technical details or URLs. This skill provides real-time access to live documentation and verifies every claim by reading the actual page content rather than relying on search snippets.

    Use cases

    • Researching breaking changes in new library versions or framework releases.
    • Finding ISO-certified hardware manufacturers in specific manufacturing hubs like Shenzhen.
    • Debugging obscure error codes by searching GitHub issues and technical forums.
    • Conducting competitor analysis and price comparisons across retail marketplaces.

    Known limitations

    JavaScript rendering requires a remote Cloudflare Worker with a BROWSER binding. The free search stack may occasionally be subject to rate limits from public engines like DuckDuckGo.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scanned

    Verified clean 11 days ago

    • Passed all security checks, Safe to install

    Listed11 days ago

    What's inside

    Frequently Asked Questions