screaming-frog-mcp
Enables automated site-wide security and compliance audits without manual intervention, reducing gap detection cycles and integrating crawl validation direct…
Headless MCP server for Screaming Frog SEO Spider – run crawls, export and analyze crawl data via the CLI. Small locked-down tool surface for scheduled audits, CI, and unattended AI agents.
- Ask Claude to crawl a website and identify all broken links before deployment.
- Generate a security compliance report by analyzing crawl data for exposed sensitive information.
- Automate weekly SEO audits to detect metadata issues across thousands of pages.
Enables automated site-wide security and compliance audits without manual intervention, reducing gap detection cycles and integrating crawl validation directly into CI/CD pipelines for continuous risk monitoring.
DevOps and security teams automating scheduled site crawls and compliance checks in headless or unattended environments.
https://github.com/bzsasson/screaming-frog-mcp
By bzsasson
How to Get It
uv tool install screaming-frog-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Crawl a website and identify all broken links before deployment
Trust Signals Auto-scanned
Data & Access
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 66 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Screaming Frog's crawl database allows one process at a time — you must close the SF GUI before the server can read or export crawl data (it detects this and errors clearly). Avoid uvx in MCP client configs: cold-cache resolution can exceed the 60-second initialize timeout; use a persistent uv tool or pip install instead. Deliberately limited to nine read-and-export tools — no script runner or filesystem writes.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 66 GitHub stars; contributors unknown; last commit 0d ago; license MIT.