Screaming Frog Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Screaming Frog Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server that exposes Screaming Frog SEO Spider crawl data as tool calls for any MCP-compatible AI assistant.
Built on top of the screamingfrog Python library.
.dbseospider files with Derby backend).seospider conversion)git clone https://github.com/acamolese/screaming-frog-mcp.git
cd screaming-frog-mcp
pipx install -e .Or with pip in a virtual environment:
pip install -e .After installation, find the full path to the command:
which screaming-frog-mcpYou will need this path for the configuration below (typically ~/.local/bin/screaming-frog-mcp when installed via pipx).
The MCP server needs to be registered in the config file of your MCP client. The file location and format vary depending on the client you use.
Add to ~/.claude/.mcp.json:
{
"mcpServers": {
"screaming-frog-seo": {
"type": "stdio",
"command": "/full/path/to/screaming-frog-mcp"
}
}
}Add to ~/Library/Application Support/Claude/claude_desktop_config.json, inside the existing mcpServers object:
{
"mcpServers": {
"screaming-frog-seo": {
"command": "/full/path/to/screaming-frog-mcp"
}
}
}Note: Claude Desktop does not use the "type": "stdio" field. If the file already contains other MCP servers, just add the "screaming-frog-seo" entry alongside them.
Refer to your client's documentation. The server uses stdio transport and the command is the path to screaming-frog-mcp.
Important: Always use the absolute path to the command (from which screaming-frog-mcp) rather than just the name, to avoid PATH resolution issues.
After editing the config, restart the application or session for changes to take effect.
| Tool | Description |
|---|---|
load_crawl | Load a crawl file |
crawl_summary | Get crawl statistics |
get_pages | Query pages with filters (status code, indexability, text search, section) |
get_links | Query inbound/outbound links |
broken_links_report | Broken links report |
title_meta_audit | Title and meta description audit |
indexability_audit | Non-indexable pages |
redirect_chains_report | Redirect chains |
canonical_issues_report | Canonical tag issues |
hreflang_issues_report | Hreflang issues |
orphan_pages_report | Orphan pages |
security_issues_report | Security issues |
redirect_issues_report | Redirect issues |
nofollow_inlinks_report | Nofollow inbound links |
compare_crawls | Compare two crawls |
query_tab | Access any crawl tab |
list_tabs | List available tabs |
list_crawls | Discover available crawls on the machine |
A ready-made slash command is available that runs a full technical SEO audit in one step. Copy the command file to your commands directory:
mkdir -p ~/.claude/commands
curl -o ~/.claude/commands/analyze-crawl.md \
https://raw.githubusercontent.com/acamolese/screaming-frog-mcp/main/commands/analyze-crawl.mdThen type /analyze-crawl in a new session. The command will ask for your crawl file and automatically run all audits, presenting a structured report.
.dbseospider (Derby, native DB-mode format).seospider (Screaming Frog project, requires CLI installed).duckdb (DuckDB cache).db (SQLite legacy)MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.