VOOZH about

URL: https://apify.com/vojtech.kaiser/actor-deep-web-search-mcp

โ‡ฑ MCP Deep Web Search ยท Apify


Pricing

Pay per usage

Go to Apify Store

MCP Deep Search Server is a cloud-based tool for advanced research, combining real-time results from Google, Brave, Anthropic, OpenAI, Perplexity, and xAI. Now hosted in the cloud, it offers faster performance with no local installation needed.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

๐Ÿ‘ Vojtech Kaiser

Vojtech Kaiser

Maintained by Community

Actor stats

6

Bookmarked

14

Total users

0

Monthly active users

a year ago

Last modified

Categories

Share

๐Ÿ‘ License: MIT

Apify MCP Deep Search

MCP Deep Search by Apify is a wrapper around MCP Deep Web Search provided by @just-every GitHub. It allows users to conduct complex research utilizing real time search across multiple search engines and models such as Google, Brave, Anthropic, OpenAI, Perplexity, and xAI. The MCP Deep Search Server now runs in a cloud environment and not locally on your computer.

Click to see how

You can limit the search to a single search engine or utilize multiple.

๐Ÿ”ง Tools

  • deep_search
    Perform deep web searches to find current information, research topics, or answer questions using real-time data from multiple search providers. Use this when you need up-to-date information beyond your knowledge cutoff.

    • query - Your prompt / question
    • provider - select none or one from these providers: anthropic, brave, brave-images, openai, google, xai, sonar. If you don't select any, the tool shall select one to yield the best results. It is recommended though to specify it.
  • comprehensive_research
    Perform in-depth research on complex topics using AI agents that automatically search multiple sources, analyze findings, and compile comprehensive reports. Ideal for thorough investigations, market research, technical analysis, or any topic requiring deep understanding from multiple perspectives.

    • query - Your prompt / task / question
    • modelClass
      • default - reasoning_mini
      • options - 'standard' | 'mini' | 'reasoning' | 'reasoning_mini' | 'monologue' | 'metacognition' | 'code' | 'writing' | 'summary' | 'vision' | 'vision_mini' | 'long' | 'image_generation' | 'embedding' | 'voice' | 'transcription';

โš ๏ธ Caveat

Tool comprehensive_research runs LLM models and engines matching the provided API keys. If any of the API keys doesn't have enough credits, the task will fail and all the API calls will irreversibly burn your credits.

Organization verification for OpenAI

The streaming ability is conditioned by verification of the organization which API key is being used. If the organization is not verified, the comprehensive research will never finish successfully as long as you provide your OPENAI_API_KEY on the actor start.

This happens for modelClasses: 'reasoning_mini' and maybe some others. Try to set standard.

How to use it

Provide API keys and start the standby actor.

Search in the logs for the URL on which the server is exposed.

Copy this URL and build the final URL for your client:

HTTP STREAMABLE:

{
"mcpServers":{
"apify-deep-search":{
"type":"mcp",
"url":"<URL>/mcp",
}
}
}

SSE (legacy):

{
"mcpServers":{
"apify-deep-search":{
"type":"sse",
"url":"<URL>/sse",
}
}
}

How to start Actor in Standby mode

  1. Provide input in the actor UI
  2. Create a task by clicking the "Create Task" in the top-right corner
  3. This should open the Task tab. If not, Tab > Standby Tasks > Your Task
  4. Tab Standby
  5. Click the "Test endpoint" button

If the request failed, check that the input contains all the required fields.

Environment Variables

Chat with MCP using Inspector client

  1. Install Inspector on your PC and start it
$npx @modelcontextprotocol/inspector
  1. Click the link with token which opens the Inspector in the browser. If Proxy Session Token is missing (Configuration > Proxy Session Token), copy it from the terminal manually.
  2. Set inspector to Streamable HTTP
  3. Provide URL Example: <URL>/mcp
  4. Set request timeout to 300000ms - Configuration > Request Timeout
  5. Connect
  6. Start chatting

Note: The standby server gets shut down after about 10 minutes of inactivity. If that happens, send a message to wake the server up and reconnect the Inspector client.

Billing

This actor doesn't charge for any calls. User only pays for the running server.

Credits

All credits go to the creators of the MCP Deep Search server.

GitHub
NPM

You might also like

Deep Research MCP - Web Search for AI Agents

renzomacar/deep-research-mcp

Give your AI agent the web: multi-source search, clean-markdown page reading, and one-call deep research dossiers. No OpenAI/Perplexity key required โ€” your agent does the synthesis. MCP server, pay-per-event.

2

Brave Search MCP Server

agentify/brave-search-mcp-server

The Brave Search MCP Server powers query processing and data handling for Brave Search, enabling fast and private search results.

Brave Search MCP Server - Super-Fast Web, Image & AI Answers

clearpath/brave-search-mcp

Search web, images, and videos through AI agents via MCP. Get AI answers with source references. 4 tools: web search with discussions/news/FAQ/locations, image search (200 results), video search (60 results), and AI answers. No Brave API key needed. Works with Claude, ChatGPT, any MCP client.

Deep Knowledge Mcp Server

eager_cornet/deep-knowledge-mcp-server

Deep Knowledge MCP Server gives LLMs real-time access to fresh technical docs using Google Search and web crawling. Instead of a basic scraper, it acts as a live knowledge engine for Claude or Cursor, letting developers instantly fetch and understand new libraries, and frameworks to code faster.

4

5.0

Brave Search Scraper

searchapi/brave-search-scraper

Scrapes organic web search results from Brave Search (search.Brave.com). Extracts title, link, snippet, domain, and date.

Brave Search Scraper

codingfrontend/brave-search-scraper

Scrapes organic web search results from Brave Search (search.Brave.com). Extracts title, link, snippet, domain, and date.

๐Ÿ‘ User avatar

Coding Frontned

2

Corporate Deep Research MCP

ryanclinton/corporate-deep-research-mcp

Deep corporate intelligence combining financial health, reputation risk, and governance analysis for AI agents via the Model Context Protocol.

5

1.0

Ffmpeg Cloud Mcp

whitewalk/ffmpeg-cloud-mcp

Cloud-based FFmpeg video/audio processing via MCP. Transcode, trim, extract audio, generate thumbnails, resize, compress, merge videos, create GIFs, and add watermarks. No FFmpeg installation needed. Works with Claude Desktop, Cursor, and any MCP client.

Video Downloader โœ… | No proxy needed

x_guru/video-downloader

Download videos from YouTube, Twitch and Kick in one tool. No proxy needed. Save to Apify storage or your own cloud (AWS S3, Azure, Google Cloud).

๐Ÿ‘ User avatar

Hundevmode Labs

2

Related articles

Build and deploy MCP servers in minutes with a TypeScript template
Read more
Best MCP servers for developers
Read more
What is MCP? Insights from the Developers Summit
Read more