Selenium MCP Server
MCP server for crawling and extracting data from web pages using Selenium with CSS/XPath selectors. Supports 17 tools including smart extraction, pagination, infinite scroll, and screenshots.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Tai-DT
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
extractFetch a web page with Selenium and extract data.
analyze_pageAnalyze a web page structure before extraction. Returns detected page type, element counts, and suggested selectors. Use this first to understand the page structure, then use extract() with appropriate selectors. - url: page URL (http/https) - headless: run browser headless (default True) - wait_for…
smart_extractSmart extraction - automatically detects and extracts content. - url: page URL (http/https) - extract_type: "auto", "products", "article", or "all" - auto: detect page type and extract accordingly - products: extract product listings - article: extract article content - all: extract everything (SEO,…
crawl_all_pagesAutomatically crawl multiple pages following pagination. - url: starting page URL - extract_type: "products" or "article" - max_pages: maximum number of pages to crawl (default 10) - headless: run browser headless (default True) - wait: seconds between page loads (default 1) - normalize_prices: conv…
crawl_infinite_scrollCrawl pages with infinite scroll / lazy loading. - url: page URL - max_scrolls: maximum scroll attempts (default 20) - scroll_pause: seconds between scrolls (default 1.5) - headless: run browser headless (default True) - normalize_prices: convert prices to structured format - dedupe: remove duplicat…
discover_siteDiscover site structure: sitemap, categories, navigation links. - url: any page on the site Returns sitemap URLs (if found), category pages, and navigation links. Useful for planning a full site crawl.
crawl_category_listCrawl multiple category URLs and extract all products. - urls: list of category page URLs to crawl - max_pages_per_category: max pagination pages per category (default 5) - headless: run browser headless - wait: seconds between pages - normalize_prices: convert prices to structured format Returns al…
export_resultsExport extracted data to file. - data: list of extracted items (from smart_extract, crawl_all_pages, etc.) - filename: output filename (default: export.csv) - format: "csv" or "json" (default: csv) Returns path to exported file.
deep_crawlDeep crawl: extract items from listing page, then visit each detail page. - url: listing page URL (category, search results, etc.) - follow_links: what links to follow - "products": follow product links and extract product details - "articles": follow article links and extract content - "all": follo…
extract_product_detailsExtract detailed product information from a list of product URLs. - urls: list of product page URLs - headless: run browser headless (default True) - wait: seconds between page loads (default 1) - normalize_prices: convert prices to structured format Returns detailed product information for each URL…
take_screenshotCapture a screenshot of a webpage. - url: page URL to capture - filename: output filename (auto-generated if not provided) - full_page: capture full page or just viewport (default True) - headless: run browser headless (default True) - wait: seconds to wait after page load (default 1) - wait_for: op…
take_element_screenshotCapture screenshot of a specific element on a page. - url: page URL - selector: CSS or XPath selector for the element (e.g., "css:.product-image") - filename: output filename (auto-generated if not provided) - headless: run browser headless (default True) - wait: seconds to wait after page load (def…
manage_cookiesManage browser cookies - get, set, or clear. - url: page URL to navigate to - action: "get" (retrieve cookies), "set" (add cookies), "clear" (delete all), "delete" (delete specific) - cookies: list of cookie dicts for "set" action, format: [{"name": "key", "value": "val", ...}] - headless: run brows…
login_and_extractLogin to a website and then extract data from a protected page. - login_url: URL of the login page - target_url: URL to extract data from after login - username_selector: CSS/XPath selector for username input - password_selector: CSS/XPath selector for password input - submit_selector: CSS/XPath sel…
execute_javascriptExecute custom JavaScript on a page and return the result. - url: page URL - script: JavaScript code to execute (use 'return' to get a value back) - headless: run browser headless (default True) - wait: seconds to wait after page load (default 1) - wait_for: optional selector to wait for before exec…
get_page_metricsGet performance metrics and page statistics. - url: page URL to analyze - headless: run browser headless (default True) - wait: seconds to wait for page to fully load (default 2) Returns performance timing, resource counts, console logs, etc.
export_to_pdfExport a webpage to a PDF file using Chrome Print-to-PDF. - url: page URL to export - filename: output filename (auto-generated if not provided) - headless: must be True for PDF export to work - wait: seconds to wait for page to stabilize (default 2) - print_background: include background colors and…
CRAWLER_HEADLESSCRAWLER_MAX_RETRIESCRAWLER_PROXY_LISTCRAWLER_LOG_LEVELTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
17/17 tools missing one or more hints — extract (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_page (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); smart_extract (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — export_results (line 910: with open(filepath, 'w', encoding='utf-8') as f:)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool handlers catch errors
16/17 tool handlers wrap calls in try/catch (94%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
export_results: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tai-dt/mcp-crawler)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check