LinkVet
Server Details
Verify before you cite: URL checks, quotes, page-to-Markdown, metadata, schema, links, archives.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools target a distinct action or output: single vs. batch URL checks are explicit, and page_metadata, schema_extract, and read_page return different layers of a page. Minor overlap remains between broken_links and check_urls, and between find_feeds and page_metadata’s feed links, so an agent may occasionally need to read descriptions carefully.
All names use snake_case and are readable, with check_* and other action verbs forming most of the set. A few names are noun-first (broken_links, page_metadata, wayback_snapshot), so it is not a pure verb_noun convention.
11 tools is well within the sweet spot for this scope, and each maps to a concrete verification, extraction, or discovery operation. No filler tools are apparent.
The set covers the core link/citation verification lifecycle: live checks, batch checks, broken-link scans, content/metadata/structured-data extraction, robots and feed discovery, quote verification, and Wayback fallback. Minor gaps like general-purpose link extraction or domain/DNS/SSL checks are workaroundable and not central to the stated purpose.
Available Tools
11 toolsbroken_linksFind broken links on a pageARead-onlyIdempotentInspect
Fetch a page, collect its unique outbound/internal links and check each one (in parallel) for 404s, timeouts and connection errors. Returns broken links with their anchor text and the status of every link checked (up to 25 per call).
Inputs: url (required), limit.
check_emailCheck an email address's domain can receive mail (DNS only)ARead-onlyIdempotentInspect
Validate an email address without sending anything: RFC syntax, whether the domain exists, MX records (or implicit A record / null MX), SPF and DMARC presence, and flags for disposable, free-provider and role addresses (info@, support@). Proves the domain accepts mail, not that the mailbox exists.
Inputs: email (required).
check_robotsCheck robots.txt rules for a URL (incl. AI bots)ARead-onlyIdempotentInspect
Is a given user agent allowed to fetch this URL under the site's robots.txt (RFC 9309 longest-match rules)? Returns allowed, matched_rule, crawl_delay, declared sitemaps, a per-bot verdict for 20 AI/search crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot...), and whether the site publishes /llms.txt.
Inputs: url (required), user_agent.
check_urlCheck a URL before citing itARead-onlyIdempotentInspect
Fetch a URL and verify it is live before you cite or share it. Returns status (live | 404 | blocked | timeout | error | invalid | blocked_ssrf), HTTP code, final URL after redirects, page title, detected price, published/modified dates, and safe_to_cite with a reason. Results are cached ~12h.
Inputs: url (required).
check_urlsCheck up to 25 URLs at onceARead-onlyIdempotentInspect
Batch version of check_url: verify up to 25 URLs in one call (e.g. every link in an answer you are about to send). Returns one result per URL in input order.
Inputs: urls (required).
find_feedsFind a site's RSS/Atom/JSON feeds and sitemapsARead-onlyIdempotentInspect
Discover the RSS, Atom and JSON feeds and the XML sitemaps for a page or site: reads , robots.txt Sitemap lines, and probes common paths (/feed, /rss.xml, /atom.xml, /sitemap.xml...). Probed results are verified by content sniffing.
Inputs: url (required).
page_metadataGet a page's title, description, Open Graph and Twitter tagsARead-onlyIdempotentInspect
Fetch a public page and return its SEO/social metadata: title, meta description, canonical URL, language, robots directive, all Open Graph (og:), Twitter card and article: tags, author, published/modified dates, hreflang alternates and feed links. Use it to build link previews or citations.
Inputs: url (required).
read_pageRead a web page as clean Markdown (with token count)ARead-onlyIdempotentInspect
Fetch a public URL and return its main content as clean Markdown (navigation, scripts, footers removed; links absolutized), plus title, final URL and an estimated token count, truncated to max_tokens. Cheaper on context than raw HTML.
Inputs: url (required), max_tokens, include_links.
schema_extractExtract JSON-LD / schema.org structured dataARead-onlyIdempotentInspect
Extract schema.org structured data from a page: every JSON-LD block (flattening @graph), the list of @types (Product, Article, Recipe, Event, Organization, FAQPage...), up to 30 typed items with their fields (prices, ratings, dates, authors), plus microdata itemtypes. Great for pulling clean product/article facts.
Inputs: url (required).
verify_quoteVerify a quote appears on a pageARead-onlyIdempotentInspect
Before you attribute a quote to a source, check that the exact words really appear on that page. Returns found (true only for verbatim or punctuation/case-only differences), match_type (exact | normalized | near | partial | none), similarity 0-1, the closest_match text actually on the page with surrounding context, and safe_to_quote. Use closest_match to correct misquotes.
Inputs: url (required), quote (required).
wayback_snapshotFind an archived copy (Wayback Machine)ARead-onlyIdempotentInspect
Find the Internet Archive Wayback Machine snapshot of a URL closest to a date (or the latest). Returns snapshot_url and time. Use it to cite a dead page (when check_url says 404) or to show what a page said at a past date.
Inputs: url (required), timestamp.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Live web checks for AI agents: sitemaps, robots.txt, URL status, broken links, feeds, citations.
Link-preview metadata and clean page-to-Markdown for any public URL. No install.
Exact source text, not summaries: check citations and quotes in one call; read pages and PDFs.
Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to fact-check claims, verify citations, and check source freshness using Wikipedia, Wikidata, Crossref, and Wayback Machine.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to verify citations and bibliographies and to check whether source documents support factual claims, using local inference, exact evidence provenance, and deterministic verdicts.1MIT
- AlicenseAqualityBmaintenanceEnables agents to verify whether citations exist and match canonical records, and whether URLs resolve and contain expected content, with evidence-backed confirmed, contradicted, or unknown verdicts.245 PyPIMIT
- AlicenseNot gradedqualityFmaintenanceValidates URLs and checks their reputation to help identify AI hallucinations and verify web page authenticity.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.