Screaming Frog SEO Spider MCP Server

Documentation

Documentation link · transport

Tools

• sf_list_crawls — Retrieves a list of recent web crawl jobs, ordered chronologically with the most recent first. Defaults to the 10 latest crawls.
• sf_load_crawl — Loads a crawl into the SEO Spider application.
• sf_export_crawl — Export the currently loaded crawl.
• sf_crawl — Starts a crawl with optional config.
• sf_pause_crawl — Pauses a running crawl.
• sf_resume_crawl — Resumes a paused crawl.
• sf_clear_crawl — Clear a paused crawl.
• sf_crawl_progress — Get the progress of a running crawl.
• sf_generate_report — Generates a report for the requested category. Use sf_list_available_reports to get a list of all available reports.
• sf_generate_bulk_export — Generates a bulk export for the requested category. Use sf_list_available_bulk_exports to get a list of all available bulk exports.
• sf_bulk_export_page_content — Bulk-exports page content for all crawled HTML URLs in NDJSON format.
• sf_export_seo_element_urls — Export URLs and associated data for a specific SEO element name and filter. The export format is NDJSON. Fields with value null mean the information is unavailable — do not guess or infer missing values. Call sf_list_available_filters_for_seo_element for filter names.
• sf_export_embeddings — Generates a CSV file with the URL and embeddings.
• sf_get_url_screenshot — Get the stored screenshot of the web page for the URL. Returns a base64 encoded image string if no file path is supplied.
• sf_url_info — Generates a JSON report with information on the supplied URL.
• sf_url_content — Get the content of a specific URL in the loaded crawl. If the URL is an image, generates base64 encoded image content. If the URL has HTML content type, generates the text content.
• sf_url_links — Lists all of the URL inlinks or outlinks depending on the links_direction argument.
• sf_open_url_in_browser — Opens the URL or absolute file path in an external browser.
• sf_list_available_reports — Lists all available reports.
• sf_list_available_bulk_exports — Lists all available bulk exports.
• sf_list_available_filters_for_seo_element — List the available filters for the supplied SEO element name.
• sf_list_available_data_fields_for_seo_element_and_filter — List the available data fields for the supplied SEO element name and filter type.
• sf_run_node_js_script — Runs the node.js script with the supplied optional arguments.
• sf_npm_install — Executes npm install to install a specific package.
• sf_read_text_file — Read the contents of a text file.
• sf_write_text_file — Writes UTF-8 content to a text file. Caution — will overwrite existing files without warning.
• sf_list_allowed_base_directory — Returns the allowed base directory that this server can access for reading and writing files. Subdirectories are also accessible.
• sf_list_directories — Get a detailed listing of all files and directories in a specified relative path. Results distinguish files and directories with [FILE] and [DIR] prefixes. Only works within allowed directories.
• sf_create_directory — Create a new directory or ensure a directory exists. Can create multiple nested directories in one operation. Only works within allowed directories.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.