Screaming Frog SEO Spider MCP Server (headless)
This connects Claude to the Screaming Frog SEO Spider CLI, letting you run crawls, export reports, and query crawl data without touching the GUI. You get tools for launching headless crawls, listing saved crawls by database ID, exporting any combination of tabs (Internal:All, Response Codes, Page Titles), bulk exports (inlinks, outlinks), and reading the resulting CSVs with filtering. The workflow is: crawl in the GUI with your custom config, close it to release the database lock, then use the MCP to slice and analyze the results. Best for automating SEO audits or building AI-powered site analysis workflows that need real crawl data instead of one-off requests. Requires a paid Screaming Frog license for most features beyond basic 500-URL crawls.
- GitHub stars
- 94
- tools
- 9
- transport
- STDIO
- env var
- 1
- last updated
- Oct 17, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
sf_checkVerify Screaming Frog is installed, check version and license status
Verify Screaming Frog is installed, check version and license status
No parameter schema in public metadata yet.
crawl_siteStart a headless background crawl (see note below)
Start a headless background crawl (see note below)
No parameter schema in public metadata yet.
crawl_statusCheck progress of a running crawl
Check progress of a running crawl
No parameter schema in public metadata yet.
list_crawlsList all saved crawls with their Database IDs
List all saved crawls with their Database IDs
No parameter schema in public metadata yet.
export_crawlExport crawl data as CSV files (many export options available)
Export crawl data as CSV files (many export options available)
No parameter schema in public metadata yet.
read_crawl_dataRead exported CSV data with pagination, filtering, and column selection
Read exported CSV data with pagination, filtering, and column selection
No parameter schema in public metadata yet.
aggregate_crawl_dataCounts and group-by breakdowns over exported data ("how many 404s", "status code distribution") without reading rows into context
Counts and group-by breakdowns over exported data ("how many 404s", "status code distribution") without reading rows into context
No parameter schema in public metadata yet.
delete_crawlPermanently delete a crawl from the database
Permanently delete a crawl from the database
No parameter schema in public metadata yet.
storage_summaryShow disk usage of SF's crawl storage
Show disk usage of SF's crawl storage
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
SF_CLI_PATHPath to the Screaming Frog SEO Spider CLI executable. Defaults to the standard macOS location.
Readme
Screaming Frog SEO Spider MCP Server (headless)
A headless MCP (Model Context Protocol) server for Screaming Frog SEO Spider. It drives the SF command line and saved crawl database directly, so Claude (or any MCP-compatible client) can run crawls, export crawl data, and analyze the results with the Screaming Frog GUI closed: on your laptop, on a server, or inside scheduled audits and CI pipelines.
This is a community project, not affiliated with Screaming Frog. Since SEO Spider v24 there is also an official MCP built into the app. The two work differently and solve different problems.
How this differs from the official Screaming Frog MCP
Details
- Repository
- github.com/bzsasson/screaming-frog-mcp
- Categories
- Sales & Marketing, Web & Browser Automation, Search & Web Crawling, Data & Analytics
- Package
screaming-frog-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Sales & Marketing MCP servers
View all
BuiltWithbuiltwith/builtwith-mcpOfficial BuiltWith tools for website technologies, company research, relationships, and trends.43stars
Lightcmsjonradoff/lightcmsAI-native, open-source CMS (Go) with 128 MCP tools: content, agent sandbox, SEO & AI.34stars
Openregistrysophymarine/openregistryLive data from 80+ official national company registries. Unmodified. For KYB and due diligence.23stars
Agent Taskskeshrath/agent-tasksPipeline task management for AI agents - stages, dependencies, artifacts, claiming22stars
BoondManager MCP Serverfauguste/boondmanager-mcp-serverMCP Server for BoondManager API - 182 tools, 12 prompts, 22 resources (ERP/CRM)21stars
Mcp Zuulimatza-rh/mcp-zuulZuul CI — build failure analysis, log search, pipeline status, and job configuration21stars