Data · Local MCP server
Screaming Frog SEO Spider MCP Server (headless)
Headless Screaming Frog SEO Spider via its CLI: run crawls, export and filter data, no GUI needed.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.bzsasson/screaming-frog-mcp- Version
- 0.4.1
- Status
- Active
- Category
- data
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-08-31
- Updated
- 2026-08-31
- Publisher
- bzsasson (GitHub) · 2 servers with pages here
- Repository
- github.com/bzsasson/screaming-frog-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | screaming-frog-mcp | 0.4.1 | stdio |
How to connect Screaming Frog SEO Spider MCP Server (headless)
Screaming Frog SEO Spider MCP Server (headless) runs locally from a Python package published to PyPI: screaming-frog-mcp version 0.4.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx screaming-frog-mcp. It reads the environment variable SF_CLI_PATH; set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"screaming-frog-mcp": {
"command": "uvx",
"args": [
"screaming-frog-mcp"
],
"env": {
"SF_CLI_PATH": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from bzsasson (GitHub)
| Server | Runs |
|---|---|
| LiveTrafficCam MCP ServerLive US traffic cameras from state DOT feeds with verified live status, via livetrafficcam.com. | Local · stdio |
More data servers
| Server | Runs |
|---|---|
| ScrapiqAny URL to clean text, markdown, or JSON for LLM/RAG pipelines. | Remote · HTTP |
| Scrapling MCP ServerWeb scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. | Local · stdio |
| ScrappaScraping API for Google Search, Maps, Flights, Jobs, YouTube, LinkedIn, Trustpilot and more. | Remote · HTTP |
| ScrappycocoRoute web, social, and filings data tasks to available scraper. | Remote · HTTP |
| ScreensDesignResearch mobile apps, onboarding, paywalls, and competitors with real screens, flows, and reviews. | Remote · HTTP |
| screenshotink.comScreenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents. | Remote & Local · HTTP, stdio |
| ScreenshotlineScreenshot any web page, or read it as clean Markdown, with consent banners, ads and popups removed. | Remote · HTTP |
| SdcgovernanceGovernance validation for Semantic Data Charter instances; returns OASIS XACML decisions. | Local · stdio |