Seo Crawler Mcp

io.github.houtini-aiPublished by GitHub account houtini-aiv2.0.1Updated Oct 24, 2026

Crawl and analyse websites for SEO errors using Crawlee with SQLite storage

VerifiedSTDIODesktop onlyWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Deprecated local MCP server that crawls a website into SQLite and lets an assistant run SEO analysis queries over the crawl results.

What you can do
  • Crawl a site and store the pages in a local SQLite database
  • Run analysis queries over the crawl to surface SEO errors
  • Report findings from the stored crawl data
  • Save crawl results to a configured output directory
When to use it
Only if you already depend on it or need a simple local site crawl with SQLite-backed SEO checks. New users are pointed to the successor project, SEO Audit Console, which adds Search Console and DataForSEO data.
Requirements
Runs as a local stdio process installed from the npm package @houtini/seo-crawler-mcp, so Node.js is needed. The OUTPUT_DIR environment variable is required and must point to a directory where crawl results are saved; DEBUG can be set to 'true' for verbose logging. Network access to the target site is needed for crawling.
Before you install
The package is deprecated and the repository is archived, with no further releases and closed issues and pull requests. Crawling sends requests to the target site and writes crawl data to the directory given in OUTPUT_DIR. The README directs users to a different successor project for new setups.

Installation

In SourceWeft

  1. Open Seo Crawler Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

SEO Crawler MCP - retired

This project has been superseded by SEO Audit Console.

SEO Crawler crawled your whole site into SQLite and gave Claude 25+ analysis queries over the result. The crawler survived the move - it was rewritten to be stdio-safe and it is now the crawl half of a bigger tool.

SEO Audit Console keeps the crawl and adds the thing the crawl could never tell you on its own: what people actually searched for to get there. It merges the crawl with your Google Search Console history and on-demand DataForSEO data, then ranks every finding by the clicks it could recover rather than by severity.

A flat crawler sells you severity. This ranks by yield.

Where to go

bash
git clone https://github.com/houtini-ai/seo-audit.git

Docs and setup: github.com/houtini-ai/seo-audit

What this means for you

  • The npm package still installs. @houtini/seo-crawler-mcp is deprecated, not unpublished. Nothing you have running will break.
  • This repository is archived. The code stays readable and every existing link keeps working, but there are no further releases, and issues and pull requests are closed.
  • The crawler got better on the way over. It no longer depends on Crawlee (which logged to stdout and corrupted MCP's JSON-RPC framing), it seeds discovery from sitemaps and known GSC URLs rather than links alone, and it guards against redirects that wander off-host.

Migrating

Start a crawl on the new tool and it builds its own database:

start_crawl for https://example.com/

Run refresh_property instead if you want the crawl, the Search Console sync and URL inspection in one pass.

Part of the Houtini open-source MCP set. Questions: [email protected].

Source: README.md at commit cd222dc

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v2.0.1LatestSep 16, 2026

Score

50% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • 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