Web Crawler MCP by InsightfulPipe

com.insightfulpipePublished by insightfulpipe.comv1.0.0Updated Nov 4, 2026

Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Hosted SEO crawler MCP server that lets an AI assistant audit websites, extract links and brand details, and generate sitemaps and robots.txt.

What you can do
  • Run 25+ SEO checks on a URL, including a full technical and content audit, indexability, canonical, headings, meta tags, structured data and hreflang
  • Check performance and delivery: page speed, page load, mobile responsiveness and viewport, image optimization, status codes and redirect chains
  • Inspect security and AI-crawler access: SSL certificate, security headers, robots.txt directives, llms.txt and AI bot permissions
  • Extract links, categorize internal and external links, and map internal linking opportunities
  • Extract brand design elements such as colors, fonts, buttons and logos
  • Generate XML sitemaps and robots.txt content
When to use it
Useful for SEO professionals, developers and agencies who want to run site audits, technical SEO checks, link analysis or competitor assessments conversationally instead of through a separate crawler tool.
Requirements
A remote MCP endpoint added as a custom connector or HTTP server; no local package. An InsightfulPipe account with OAuth sign-in is required, and the server is included in a paid InsightfulPipe plan starting at $29.99/month after a 7-day trial. ChatGPT access depends on plan and developer mode.
Before you install
Requires signing in to an InsightfulPipe account and a paid subscription. The server crawls the URLs you give it, so target sites and their content are fetched by a third party. Actions are read-only by default and can be toggled per account; a read-only connection cannot enable write actions.

Installation

In SourceWeft

  1. Open Web Crawler MCP by InsightfulPipe in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.insightfulpipe%2Fcrawler/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "web-crawler-by-insightfulpipe": {
      "type": "http",
      "url": "https://crawler.insightfulmcp.com/"
    }
  }
}

README

Web Crawler MCP Server (SEO Crawler) by Insightful Pipe

[MCP Compatible] [Insightful Pipe] [License]

Comprehensive SEO auditing and web crawling through AI with MCP.

Part of the Insightful Pipe MCP Server Collection — The Web Crawler MCP server enables Claude, ChatGPT, Cursor, and other AI assistants to perform SEO audits, extract data, and analyze websites. Run 25+ specialized SEO checks, generate sitemaps, and extract brand information.

[Explore All MCP Servers]

[Web Crawler MCP Server]

MCP Server URL

https://crawler.insightfulmcp.com/

What is Web Crawler MCP?

Web Crawler MCP is a remote Model Context Protocol server that provides AI assistants with comprehensive SEO auditing and web crawling capabilities. This integration allows you to:

  • Run 25+ specialized SEO checkers on any URL
  • Generate XML sitemaps and robots.txt files
  • Extract brand design elements from websites
  • Audit technical SEO, content quality, and security
  • Analyze mobile responsiveness and page speed

Installation

Claude

  1. Copy the MCP Server URL: https://crawler.insightfulmcp.com/
  2. Open Claude Connectors Settings
  3. Scroll to the bottom and click Add custom connector
  4. Paste the URL and click Add
  5. Click Connect and sign in to InsightfulPipe if asked. Claude then lists the connector as connected.

ChatGPT

Custom MCP servers are added through ChatGPT's Developer mode. Availability depends on your ChatGPT plan, and workspace admins may need to allow it.

  1. Turn on Developer mode in ChatGPT settings
  2. Create a new app for a remote MCP server and paste the URL: https://crawler.insightfulmcp.com/
  3. Sign in to InsightfulPipe if asked. The connection finishes as soon as you are signed in.

See OpenAI's guide: Developer mode and MCP apps in ChatGPT

Claude Code

bash
claude mcp add --transport http crawler https://crawler.insightfulmcp.com/

Cursor

Add the server to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

json
{  "mcpServers": {    "crawler": {      "url": "https://crawler.insightfulmcp.com/"    }  }}

When Cursor shows Needs authentication, click Connect and sign in to InsightfulPipe if asked.

Available Actions

33 actions: 33 read, 0 write.

Read Actions (33)

Show all 33 read actions
ActionDescription
ai-crawler-checkerCheck permissions for AI training bots and crawlers
amp-checkerVerify AMP implementation quality and discoverability
brand-extractorExtract brand design details from a website (colors, fonts, buttons, logos)
canonical-checkerValidate canonical URLs and conflicting hints
character-encoding-checkerValidate declared charset and encoding consistency
content-optimizer-checkerAnalyze on-page content quality and keyword density
content-quality-checkerScore readability, word count, and duplication risk
deprecated-html-checkerDetect obsolete tags or attributes still in use
favicon-checkerConfirm favicon/icon discovery across devices
headings-checkerReview heading hierarchy (H1-H6) for structure gaps
hreflang-checkerReview international hreflang annotations
image-optimization-checkerCheck alt text, formats, and compression levels
indexability-checkerReview robots/meta directives affecting indexation
internal-linking-checkerMap internal links and surface opportunities
language-checkerVerify html[lang] attributes and language targeting
link-analysis-checkerDetect broken or low-quality links on page
link-extractorExtract all links from a page and categorize them (internal and external)
llms-txt-checkerParse llms.txt instructions for AI crawlers
meta-tags-checkerInspect meta title/description tags across the page
mobile-responsive-checkerAudit responsive layout rules and breakpoints
mobile-viewport-checkerEnsure viewport meta tags and responsive meta configs are in place
page-load-checkerMeasure page weight and render-blocking assets
page-speed-checkerMeasure load times and highlight slow resources
robots-txt-checkerParse robots.txt directives and highlight blocking issues
robots-txt-generatorGenerate robots.txt content with optional AI bot restrictions
security-headers-checkerCheck CSP/HSTS and other security headers
seo-audit-checkerComprehensive SEO audit covering technical and content issues
sitemap-generatorCrawl the target domain and produce an XML sitemap
social-media-checkerValidate Open Graph and Twitter Card metadata
ssl-certificate-checkerInspect certificate chain, expiry, and HTTPS enforcement
status-code-checkerTrace HTTP status/redirect chains for a URL
structured-data-checkerValidate Schema.org markup and structured data coverage
url-structure-checkerEvaluate keyword usage and cleanliness of URLs

Control What Your AI Can Do

You decide what AI agents can do with each connected account:

  • Turn individual actions on or off for every connected account, so agents only see the actions you allow.
  • Connect as Read-only or Read & Write. A read-only connection can only enable read actions.
  • Destructive actions stay off by default. Actions such as deletes are disabled until an admin enables them.
  • Team access per account. Restricted team members only use the accounts they are granted, with the read actions enabled on them.

Usage Examples

Full SEO Audit

"Run a comprehensive SEO audit on https://example.com"

Check Technical SEO

"Check the robots.txt and indexability of https://example.com"

Analyze Internal Links

"Map all the internal links on this page"

Generate Sitemap

"Generate an XML sitemap for https://example.com"

Extract Brand Elements

"Extract the brand colors, fonts, and logos from https://company.com"

Security Audit

"Check the SSL certificate and security headers for this site"

Why Web Crawler MCP?

For SEO Professionals

  • Comprehensive audits - 25+ specialized checks
  • Technical SEO - Robots, canonical, structured data
  • Content analysis - Quality scoring and optimization

For Web Developers

  • Debug issues - Find broken links, redirect chains
  • Performance - Page speed and resource analysis
  • Security - SSL and header validation

For Agencies

  • Client audits - Quick site assessments
  • Competitive analysis - Analyze competitor sites
  • Reporting - Generate findings conversationally

Security & Privacy

  • Secure requests - HTTPS support

Pricing

The Web Crawler MCP server is included in every InsightfulPipe plan, together with all other MCP servers and the CLI. Plans start at $29.99/month, and you can try it for 7 days. See insightfulpipe.com/pricing for current plans.

Ready-Made Skills and Prompts

Explore More MCP Servers by Insightful Pipe

Visit insightfulpipe.com/mcp-servers to discover our full collection of MCP servers for marketing and analytics.

SEO & Performance MCP Servers

Analytics MCP Servers

View All MCP Servers →

Resources

Support


Insightful Pipe — AI-powered marketing analytics through MCP servers. Explore all integrations →

License

MIT License - see LICENSE for details.

Source: README.md at commit 7a050e9

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 21, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts