# Fast Agent MCP Web Search & Clean Markdown Extractor (`richigga/fast-agent-mcp-web-search-extractor`) Actor

Ultra-fast, zero-browser web search and clean LLM-optimized Markdown extractor for Cursor, Claude, LangChain, and MCP AI agents.

- **URL**: https://apify.com/richigga/fast-agent-mcp-web-search-extractor.md
- **Developed by:** [Jiani Peng](https://apify.com/richigga) (community)
- **Categories:** Developer tools, Business, AI
- **Stats:** 2 total users, 1 monthly users, 80.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## ⚡ Fast Agent MCP Web Search & Clean Markdown Extractor

[![Apify Actor](https://img.shields.io/badge/Apify-Actor-orange?logo=apify)](https://apify.com)
[![Model Context Protocol](https://img.shields.io/badge/MCP-Compliant-blue?logo=anthropic)](https://modelcontextprotocol.io)
[![Zero Browser Overhead](https://img.shields.io/badge/Speed-Sub--Second-brightgreen)]()
[![Zero External Paid API](https://img.shields.io/badge/Cost-$0%20API%20Fees-success)]()

**Fast Agent MCP Web Search & Extractor** is an ultra-fast, zero-browser web search and clean LLM-optimized Markdown extractor designed specifically for **AI Agents, Cursor, Claude Desktop, LangChain, and RAG pipelines**.

***

### 🌟 Key Features

- 🏎️ **Sub-Second Speed:** Operates entirely without heavy headless browsers (Puppeteer/Playwright), saving 90%+ RAM and compute costs.
- 🧹 **RAG-Ready Clean Markdown:** Automatically strips scripts, styles, advertisements, cookie banners, navigation bars, and footers. Returns clean GitHub-Flavored Markdown with YAML metadata (tokens, title, author).
- 🔌 **Native Model Context Protocol (MCP):** Connects directly into Claude Desktop or Cursor as an autonomous tool.
- 💰 **Zero Paid API Requirement:** Built on public, lightweight search feeds. Zero OpenAI/Perplexity/SerpApi key fees required.
- 📦 **Direct URL & Query Modes:** Supports broad web search extraction or focused batch scraping across URL arrays.

***

### 🚀 Quick Start / Input Parameters

#### Example Input (`JSON`)

```json
{
  "query": "Model Context Protocol architecture and best practices",
  "maxResults": 3,
  "extractFullContent": true,
  "mcpProtocolResponse": false
}
```

#### Parameter Details

| Field | Type | Default | Description |
| :--- | :---: | :---: | :--- |
| `query` | `string` | `""` | Search keywords to retrieve live results for. |
| `urls` | `array` | `[]` | Direct list of web page URLs to scrape and convert into Markdown. |
| `maxResults` | `integer` | `5` | Maximum number of search results to fetch (1–20). |
| `extractFullContent` | `boolean` | `true` | When `true`, scrapes the full page content into clean Markdown. |
| `includeRawHtml` | `boolean` | `false` | When `true`, includes sanitized HTML alongside Markdown. |
| `mcpProtocolResponse`| `boolean` | `false`| When `true`, wraps results into MCP `CallToolResult` JSON. |

***

### 💻 Claude Desktop & Cursor MCP Configuration

You can connect this Actor directly to Claude Desktop or Cursor via the Apify MCP connector:

```json
{
  "mcpServers": {
    "apify-web-search-extractor": {
      "command": "npx",
      "args": [
        "-y",
        "@apify/mcp-server",
        "--actor",
        "username/fast-agent-mcp-web-search-extractor"
      ],
      "env": {
        "APIFY_TOKEN": "YOUR_APIFY_API_TOKEN"
      }
    }
  }
}
```

***

### 📊 Example Output

```json
{
  "title": "Introducing Model Context Protocol",
  "url": "https://example.com/article",
  "snippet": "An open standard for AI assistants to securely access data...",
  "estimatedTokens": 412,
  "markdown": "---\ntitle: \"Introducing Model Context Protocol\"\nurl: \"https://example.com/article\"\ntokens_approx: 412\n---\n\n# Model Context Protocol\n\nModel Context Protocol (MCP) is an open standard...",
  "success": true
}
```

***

### 🏷️ Pricing & Monetization

- **Pay Per Run:** `$0.0005` per search & extraction run.
- **Monthly Rental:** `$19.00 / month` with unlimited developer runs.
- **Trial:** 50 free runs included.

***

### 🛡️ License

Apache 2.0. Built for the Autonomous Zero-Cost Money Factory ecosystem.

# Actor input Schema

## `query` (type: `string`):

Keywords or search term to look up across web results.

## `urls` (type: `array`):

List of direct URLs to scrape and convert to clean markdown instead of or in addition to search results.

## `maxResults` (type: `integer`):

Maximum number of search results to fetch and extract content for.

## `extractFullContent` (type: `boolean`):

Whether to fetch the destination pages and extract clean Markdown article content.

## `includeRawHtml` (type: `boolean`):

If enabled, includes original sanitized HTML along with the Markdown output.

## `mcpProtocolResponse` (type: `boolean`):

If true, formats the output structure as Model Context Protocol (MCP) CallToolResult.

## Actor input object example

```json
{
  "query": "latest model context protocol mcp servers best practices",
  "maxResults": 5,
  "extractFullContent": true,
  "includeRawHtml": false,
  "mcpProtocolResponse": false
}
```

# Actor output Schema

## `output` (type: `string`):

Clean Markdown extraction result for AI agents

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "query": "latest model context protocol mcp servers best practices"
};

// Run the Actor and wait for it to finish
const run = await client.actor("richigga/fast-agent-mcp-web-search-extractor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "query": "latest model context protocol mcp servers best practices" }

# Run the Actor and wait for it to finish
run = client.actor("richigga/fast-agent-mcp-web-search-extractor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "query": "latest model context protocol mcp servers best practices"
}' |
apify call richigga/fast-agent-mcp-web-search-extractor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,richigga/fast-agent-mcp-web-search-extractor"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/S249uPQcbNlpRGlYd/builds/BaDjxVIBJcNTmxe0N/openapi.json