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. Its 9 documented tools cluster into crawl, read & search, check, export.

People who work with screaming frog, seo and automation and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-31 · ★ 87 · #44 OF 255 MAINTAINED BROWSER AUTOMATION · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Screaming Frog SEO Spider MCP Server (headless)

before you install - you'll need

SF_CLI_PATH is optional or environment-specific per the README.

Claude Code

claude mcp add bzsasson-screaming-frog-mcp -- uvx screaming-frog-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "bzsasson-screaming-frog-mcp": {
      "command": "uvx",
      "args": [
        "screaming-frog-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package screaming-frog-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.bzsasson is GitHub-verified and matches the repo owner

03 · What Screaming Frog SEO Spider MCP Server (headless) can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can start a headless background crawl (see note below), check progress of a running crawl, list all saved crawls with their Database IDs, and export crawl data as CSV files (many export options available).

Capability map

Tools grouped from the project's README - what Screaming Frog SEO Spider MCP Server (headless) lets an agent do.

Crawl

2 tools - e.g. Start a headless background crawl (see note below); Check progress of a running crawl

crawl_site · crawl_status

read & search

2 tools - e.g. List all saved crawls with their Database IDs; Read exported CSV data with pagination, filtering, and column selection

list_crawls · read_crawl_data

Check

1 tool - e.g. Verify Screaming Frog is installed, check version and license status

sf_check

Export

1 tool - e.g. Export crawl data as CSV files (many export options available)

export_crawl

Aggregate

1 tool - e.g. Counts and group-by breakdowns over exported data ("how many 404s", "status code distribution") without reading rows into context

aggregate_crawl_data

delete

1 tool - e.g. Permanently delete a crawl from the database

delete_crawl

Storage

1 tool - e.g. Show disk usage of SF's crawl storage

storage_summary

Limitations (from the README)

Screaming Frog uses an internal database that can only be accessed by one process at a time. This means: > You must close the Screaming Frog GUI before the MCP server can access crawl data.

Latest releases

v0.4.1 · 2026-08-31

Regenerated the export reference from the SF 24.1 CLI (355 bulk exports, submenu-prefixed names like Content:Soft 404 Inlinks) and widened the export-name allowlist. Closes #11 - soft 404 inlinks export worked all…

v0.4.0 · 2026-06-12

New tools and parameters aimed at answering questions without flooding the model's context window, plus machine-readable safety hints. · New · aggregate_crawl_data tool. Server-side counts and group-by breakdowns over…

v0.3.4 · 2026-06-11

Documentation release. · Added TROUBLESHOOTING.md: step-by-step diagnostic guide for "Could not attach to MCP server" connection failures - manual server test, MCP handshake check, client log locations, and a symptom…

04 · Who maintains Screaming Frog SEO Spider MCP Server (headless)

Screaming Frog SEO Spider MCP Server (headless) is maintained by bzsasson. We track 2 MCP servers from bzsasson - 2 actively maintained, 87 combined GitHub stars, oldest repo from Feb 2026.

05 · Facts

repository: github.com/bzsasson/screaming-frog-mcp
category: browser automation - ranked #44 of 255 actively-maintained browser automation servers as of 2026-09-18.
release cadence: 1 release in the last 90 days (latest 2026-08-31)
registry: io.github.bzsasson/screaming-frog-mcp (active, first published 2026-02-28 · 3 versions)
packages: pypi:screaming-frog-mcp

06 · Screaming Frog SEO Spider MCP Server (headless) FAQ

Is Screaming Frog SEO Spider MCP Server (headless) still maintained?

Yes - as of 2026-09-18, its last commit was 2026-08-31 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can Screaming Frog SEO Spider MCP Server (headless) do?

How do I install Screaming Frog SEO Spider MCP Server (headless)?

Run `uvx screaming-frog-mcp`. The README documents one environment variable (SF_CLI_PATH) to set first. SF_CLI_PATH is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Screaming Frog SEO Spider MCP Server (headless) run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Screaming Frog SEO Spider MCP Server (headless)

Alternatives to Screaming Frog SEO Spider MCP Server (headless)

Maintained browser automation servers if Screaming Frog SEO Spider MCP Server (headless) isn't the fit.

Pairs well with

Servers that cover what Screaming Frog SEO Spider MCP Server (headless) doesn't - only shown when the pairing reason fits the companion.

More browser automation MCP servers · Antigravity Link · Agent Device (callstack) · Agent Device (callstackincubator) · GDD - AI-Controlled Browser Farm · Capawesome Team MCP Server

More Python MCP servers · Meyhem - MCP Server Discovery & Agent Search · dMoERA Creator · Chat Spatial · Gopher & Gemini MCP Server · Openzim MCP · see all