# Research MCP Server

> Research MCP Server is a paid MCP server for web search and scraping. 23 live research tools for agents, from arXiv and SEC filings to package versions. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, Web
- **Website:** https://damistudio.io/tools/research-mcp-server/
- **MCP Registry name:** io.damistudio/research-mcp-server
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

Each tool in this server is a thin front for a separate Apify scraper, and that is the main thing to understand before connecting it. The server itself charges nothing per call except for page reads from 9 November 2026, but every call starts a run of the matching scraper on your own Apify account, billed at that scraper's price. An agent looping on tools keeps starting runs, so the page advises capping tool use in the client.

The tools cover scholarly sources (arXiv, OpenAlex, Crossref, plus a literature_report that queries three at once), code and forums (GitHub, Stack Exchange, Hacker News, DEV), Wikipedia, news and web search, page reading as Markdown, SEC EDGAR filings, IMDb, npm and PyPI versions, CoinGecko markets, email deliverability checks, TikTok trends, Telegram channels and two public ad libraries. Rows are capped between 3 and 250 per call, and calls take roughly 3 to 9 seconds.

Connect with your Apify API token as a bearer header; the first call after idle time may need a retry. A toolPrefix query parameter avoids name clashes with other servers.

## Features

- **Scholarly search:** arXiv, OpenAlex and Crossref, with literature_report merging all three by topic.
- **Code and community:** GitHub repositories, Stack Exchange, Hacker News and DEV Community posts.
- **Web search and reading:** Search results, page text as Markdown, and a combined search-and-read tool.
- **Filings and packages:** SEC EDGAR filings and npm or PyPI version, licence and download data.
- **Market and media data:** Crypto market caps, IMDb records and TikTok trending hashtags.
- **Ad libraries:** Google Ads Transparency and TikTok ad library lookups.
- **Per-call scraper billing:** Each call bills the scraper it runs on your Apify account.

## Good for

- Survey recent papers on a topic across three sources
- Look up a company's latest 10-K filings
- Check the current version and licence of an npm or PyPI package
- Find the ads a domain runs on Google
- Verify whether an email address looks deliverable

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http research-mcp-server https://dami-studio--research-mcp-server.apify.actor/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://dami-studio--research-mcp-server.apify.actor/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "research-mcp-server": {
      "url": "https://dami-studio--research-mcp-server.apify.actor/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "research-mcp-server": {
      "type": "http",
      "url": "https://dami-studio--research-mcp-server.apify.actor/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "research-mcp-server": {
      "serverUrl": "https://dami-studio--research-mcp-server.apify.actor/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "research-mcp-server": {
      "type": "http",
      "url": "https://dami-studio--research-mcp-server.apify.actor/mcp"
    }
  }
}
```

## Tools

- `search_arxiv`: Searches arXiv papers.
- `search_openalex`: Searches the OpenAlex scholarly graph.
- `search_crossref`: Searches Crossref records.
- `literature_report`: Searches OpenAlex, Crossref and arXiv at once.
- `search_github`: Searches GitHub repositories.
- `search_stackexchange`: Searches Stack Exchange questions.
- `search_hacker_news`: Searches Hacker News stories and comments.
- `search_devto`: Lists DEV Community posts.
- `search_wikipedia`: Searches Wikipedia articles.
- `search_news`: Returns current news headlines.
- `web_search`: Returns web search results.
- `read_page`: Reads a public web page as Markdown or text.
- `search_and_read`: Searches then reads the top pages.
- `search_or_read`: Reads a web address or searches anything else.
- `search_sec_filings`: Finds SEC EDGAR filings.
- `search_imdb`: Searches films, TV series and people.
- `lookup_package`: Looks up npm or PyPI packages.
- `crypto_markets`: Lists top cryptocurrency markets.
- `verify_email`: Checks whether an address looks deliverable.
- `tiktok_trending_hashtags`: Lists trending TikTok hashtags.
- `telegram_channel`: Reads recent posts from public Telegram channels.
- `google_ads_for_domain`: Lists ads a website runs on Google.
- `search_tiktok_ads`: Searches TikTok's public ad library.

## FAQ

### What do I need to connect?

An Apify account and its API token, sent as a Bearer header or a token query parameter.

### How does billing work?

Each call runs a scraper on your Apify account at its own price. From 9 November 2026 page reads add $0.60 per 1,000 pages on the Free plan.

### Are repeated calls charged twice?

An identical call within about a minute is answered from memory and starts no new run.

### How many rows come back?

Between 3 and 250 rows per call depending on the tool.

### Is Research MCP Server free?

No. Research MCP Server is a paid product.

### How do I add Research MCP Server to Claude Code?

Run this command in your terminal: claude mcp add --transport http research-mcp-server https://dami-studio--research-mcp-server.apify.actor/mcp

### What are the best alternatives to Research MCP Server?

The closest alternatives to Research MCP Server are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/research-mcp-server
