mcpField
W
Web Research Agent

Web Research Agent

Remote
mcpize.comOther0Updated today

About Web Research Agent

Web Research Agent is an MCP server for AI agents and MCP clients that turns website research into structured company profiles, audits, extracted page data, and change checks. It offers six focused tools backed by the Web Research Agent API.

Key features

  1. 01Company profile extraction
  2. 02SEO, performance, and security audits
  3. 03Web page data as JSON
  4. 04Email and DNS checks
  5. 05Sitemap URL listing
  6. 06Page change detection

Use cases

  1. 01Research a company from its website
  2. 02Review site issues before outreach
  3. 03Extract page content for structured analysis
  4. 04Track sitemap or page changes

MCP support

Exposes six research tools to Claude, Cursor, and other MCP clients. Calls are backed by the Web Research Agent API and require a RapidAPI key, except for the hosted MCPize option.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://web-research-agent-mcp.mcpize.run/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

web-research-agent-mcp

MCP server that gives Claude, Cursor or any MCP client six research tools: company_profile, site_audit, page_to_json, email_check, sitemap_urls and page_diff. It is backed by the Web Research Agent API on RapidAPI. You need your own RapidAPI key. The free plan gives you 50 calls/month.

Setup

  1. Subscribe on RapidAPI (Free plan) and copy your X-RapidAPI-Key.
  2. Add the server to your MCP config:
{ "mcpServers": { "web-research-agent": { "command": "npx", "args": ["-y", "github:elaysuu/web-research-agent-mcp"], "env": { "RAPIDAPI_KEY": "YOUR_KEY" } } } }

Tools

  • company_profile(url): name, description, logo, socials, emails, key pages, price mentions, tech stack.
  • site_audit(url, max_links?): 0–100 score, SEO, performance, security-header and broken-link issues.
  • page_to_json(url, max_text?): meta, OG, JSON-LD, headings, links, images, clean text.
  • email_check(email? | domain?): syntax, MX/null-MX, SPF, DMARC policy, disposable/free/role flags, verdict and 0–100 score (live DNS, no SMTP probe).
  • sitemap_urls(url, limit?, max_sitemaps?, since?): every URL a site publishes in its sitemaps, with lastmod; since returns only changed pages.
  • page_diff(url, previous_text? | previous_hash?, selector?): content hash plus added/removed lines since your last check — a stateless change monitor.

The crawler respects robots.txt and refuses private and internal addresses. MIT license.

Hosted / pay-per-call

Also available hosted on MCPize with pay-per-call pricing (no RapidAPI key needed). Self-hosters of the backend can use direct mode with env WRA_DIRECT_URL and WRA_DIRECT_TOKEN.

Also by the author

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.