DomainKits MCP Server

Search active gTLD domains from a database of ~240 million registered domains. This tool is primarily a market analysis instrument — use it to understand keyword distribution, saturation, and market dynamics through comparative queries. Core analysis dimensions (typically requiring multiple calls per keyword): - TLD distribution: Compare total_found with no tld filter vs tld=com vs tld=net vs others to calculate .com concentration and cross-TLD spread. - Position distribution: Compare position=start vs position=end to gauge market maturity. Start-heavy means the keyword is used as a category anchor (e.g., 'aiwriter.com'); end-heavy means it has become a standard descriptor (e.g., 'writerai.com'). - For-sale ratio: Compare status=forsale total_found vs unfiltered total_found. High ratio (>30%) suggests speculator saturation; low ratio (<10%) suggests most holders are actively using their domains. - Quality distribution: Compare type=all_alpha total_found vs unfiltered total. If the majority of registrations contain hyphens or numbers, the keyword is dominated by low-quality or spam registrations — a negative signal. - Length distribution: Compare total_found across length filters (<5, 5-10, 11-15, >15) to assess how much premium short-name inventory exists vs long-tail. Best practices: - keyword defaults to 'contain' matching (substring). This is appropriate for statistical analysis but produces large result sets. Use position=start or position=end when analyzing directional distribution. - The total_found field across multiple filtered calls is the primary analytical output — the actual domain list is secondary. - sort=length_asc surfaces the shortest (most premium) names first when browsing results. - status=forsale filters to domains explicitly listed for sale — these are acquisition targets. - no_hyphen and no_number are independent boolean parameters, separate from the type filter. - Disclose affiliate links when presenting register_url to users.

Search currently registered domains with 5-20+ years of history. These are live domains owned by someone — not available for free registration. Use has_sale=true to filter to domains the owner has listed for sale, or use results as acquisition targets to approach owners directly. Best practices: - Always use no_hyphen=true and no_number=true unless the user specifically wants them. - keyword defaults to 'contain' matching, which searches all domains containing the keyword anywhere in the name. Use position=start, position=end, or position=middle to control where the keyword appears. - has_sale=true is the most actionable filter — these owners are actively seeking buyers. - Caution: Many aged domains are already in active use as established brands. Before recommending an aged domain to a user, consider whether it is likely an operating business — a 20-year-old short .com is almost certainly in use. - Short domains (<5 chars) with 20+ years of history are rare and typically high-value. Most 4-letter .coms were registered over 20 years ago. - For premium brand hunting: combine length=<5 or 5-10, type=all_alpha, no_hyphen=true, age_range=20+. - sort=age_desc surfaces the oldest domains first. sort=length_asc surfaces the shortest. - Disclose affiliate links when presenting register_url to users.

Comprehensive domain analyze workflow. Call when a user wants to understand a specific domain's full picture — registration status, safety, DNS configuration, cross-TLD distribution, and current website usage. When to use: user asks 'what can you tell me about example.com?', wants to evaluate a domain before purchasing, or needs a technical analyze. Do NOT use for domain name ideas (use name_advisor), availability checks (use available), or expired domain evaluation (use expired_analysis). Workflow: 1. Gather data using all four atomic tools in parallel: - whois for registration details, registrar signals, and expiry dates. - safety for Google Safe Browsing status. - dns for MX, A, and CNAME records — signals of active usage or abandonment. - tld_check to see how many TLDs share this prefix. 2. If tld_check shows high registration count, investigate further: - whois the .com/.net/.org variants to check if the same registrar holds multiple TLDs (brand protection signal) or different registrars (popular keyword signal). - web_search the TLD variants to see if they resolve to the same site. 3. Visit the domain via web_fetch or web_search to determine current usage: active business, parked page, for-sale landing, or no content. 4. Use web_search to investigate the domain's market background: recent sale history (NameBio, Sedo, Afternic), related news or brand events, legal disputes (UDRP, trademark conflicts), and any notable context that affects valuation or risk. This step is critical — technical data alone is insufficient for a complete analyze. 5. Synthesize all findings into a concise analyze report. Present facts with key signals clearly flagged. Do NOT make buy/don't-buy judgments — present evidence and let the user decide. 6. After presenting the report, ask the user about their goals before suggesting next steps. Tailor follow-up based on their answer: - Wants to purchase → suggest valuation_cma for pricing, brand_match for trademark risk. - Domain is listed for sale → provide the sale link, suggest brand_match. Disclose affiliate links. - Wants alternatives → suggest plan_b. - Wants monitoring → suggest set_monitor. Key principles: present facts, not recommendations. Flag signals clearly (e.g., enterprise registrar = corporate-held, MX present = active email, no A record = possibly abandoned). Every claim must come from tool data. Disclose affiliate links when presenting registration or sale URLs.

Check domain availability with pricing. Final validation before registration. Best practices: - Input must be a fully qualified domain name including TLD (e.g., 'example.com', not just 'example'). - If status='available': present reg_url and price clearly. If price is significantly higher than standard registration (~$10-15 for .com), flag it as a premium/reserved domain — the registry is charging a premium price. - If status='registered': state clearly the domain is taken. Do not automatically suggest alternatives — let the user decide if they want to explore other options. - If status='expiring': domain is in the expiration pipeline — can be backordered via reg_url, not directly registered. - If status='reserved': registry-reserved domain — not available for registration. - If status='unknown': check was inconclusive — do not assume available or unavailable. - For batch checking multiple domains, use bulk_available instead — it checks up to 10 at once. - This tool is the definitive availability check. Other tools (tld_check, deleted, expired) may show signals of availability, but only this tool or bulk_available confirms registrability and returns actual pricing. - Disclose affiliate links when aff=true.

Brand conflict and trademark risk detection workflow. Call when a user wants to check whether a domain name carries brand-related risks before registering or purchasing it. When to use: user asks 'is this domain safe to register?', wants to assess UDRP risk before purchase, or needs trademark conflict checking as a follow-up from name_advisor or analyze. Do NOT use for general technical analysis (use analyze), domain name brainstorming (use name_advisor), or DNS/registration checks only (use dns, whois). Workflow: 1. Extract the prefix from the domain (e.g., nicefloor.com → nicefloor). If the prefix contains a well-known brand name (google, apple, amazon, microsoft, etc.), immediately warn the user about high UDRP risk before proceeding. Ask the user about their intent: are they assessing risk before registration, or holding the domain and looking for potential buyers? This determines the framing of the analysis. Do NOT call any tools before the user responds. 2. After the user responds, gather data in parallel: - web_search '[prefix] company' to discover existing commercial use — note founding year, business scale, industry, and whether the company actively uses this keyword as a brand. - tld_check to see how many TLDs have this prefix registered. - If tld_check shows high registration, whois the .com/.net/.org variants to check if the same registrar holds multiple TLDs (brand protection signal) or different registrars (popular keyword signal). Use web_search to verify if they resolve to the same website. 3. Run trademark database checks across all four major databases. Primary method is Claude for Chrome — open each database, search for [prefix], and read results directly. If Claude for Chrome is not available, fall back to providing pre-filled links as described below. Present findings from each database inline as they come in — do not wait for all four before reporting. USPTO: - Chrome: navigate to https://search.uspto.gov/search?query=[prefix]&affiliate=web-sdmg-uspto.gov and read results directly. - Fallback (no Chrome): USPTO supports URL query parameters — provide this pre-filled link for the user to open: https://search.uspto.gov/search?query=[prefix]&affiliate=web-sdmg-uspto.gov - Extract: number of trademark hits, registrant names, goods/services classes, live vs dead status. EUIPO: - Chrome: navigate to https://euipo.europa.eu/eSearch/, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): EUIPO uses a JavaScript interface — URL parameters cannot pre-fill search. Provide the entry link and instruct the user: 'Please open https://euipo.europa.eu/eSearch/ and search for [prefix].' - Extract: EU trademark hits, registrant names, classes, status. WIPO: - Chrome: navigate to https://branddb.wipo.int/en/quicksearch, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): provide entry link and instruct: 'Please open https://branddb.wipo.int/en/quicksearch and search for [prefix].' - Extract: international trademark hits, registrant names, designating countries, status. TMview: - Chrome: navigate to https://www.tmdn.org/tmview/#/quicksearch, locate the search input, type [prefix], submit, read results. - Fallback (no Chrome): provide entry link and instruct: 'Please open https://www.tmdn.org/tmview/#/quicksearch and search for [prefix].' - Extract: aggregate hits across all participating offices, notable registrants. If a database is unreachable or returns an error, note it in the report and continue — do not halt the workflow. 4. Synthesize all findings into a report, framed according to the user's stated intent (risk-focused or opportunity-focused). The report must include: - Discovered entities: websites/companies using this keyword, their business, scale, founding year. - TLD distribution: cross-TLD registration pattern and registrar correlation. - Trademark database summary: hits per database, live marks found, relevant classes. If no hits found in a database, state that clearly — absence of results does not guarantee the mark is clear. - Risk assessment based on the three UDRP principles (confusing similarity, rights or legitimate interests, bad faith). For generic word combinations, note that risk is typically lower. Factor in registration age. Do NOT make legal conclusions. - Disclaimer: 'For reference only, does not constitute legal advice. Trademark searches are not exhaustive — consult a qualified IP attorney before making registration or investment decisions.' 5. After presenting the report, ask the user what they want to do next. Tailor follow-up based on their response: - Wants to proceed with registration → suggest available or bulk_available. - Wants deeper analysis → suggest analyze. - Wants alternatives → suggest plan_b or name_advisor. - Wants to find buyers → use web_search findings to identify potential buyers, suggest valuation_cma. - Wants monitoring → suggest set_monitor. Key principles: present facts, not legal judgments. Do NOT claim a trademark exists or does not exist based on partial results. Claude for Chrome reads all four databases directly — the user should never need to search manually when Chrome is available. When Chrome is unavailable, always provide actionable fallback links with clear search instructions. Always end with the legal disclaimer. Disclose affiliate links.

Batch check domain availability with pricing. Check up to 10 domains per call. This is the verification gate — any domain recommended to a user must pass through this tool first. Do not present domains as available based on other tools' signals (e.g., tld_check showing 'might_available', or domains found in deleted/expired feeds) without confirming here. Input format: comma-separated full domain names including TLD (e.g., 'aitools.com,getai.io,smartai.app'). Maximum 10 per call — for larger batches, make multiple calls. Interpreting results: - status 'available': Confirmed registrable. price and reg_url will be present. - status 'registered': Currently owned — not available for standard registration. - status 'expiring': In the expiration pipeline — can be backordered, not directly registered. reg_url will point to a backorder service. - status 'reserved': Registry-reserved domain — not available for registration. - status 'unknown': Check was inconclusive — do not assume available or unavailable. Best practices: - Always disclose affiliate links when aff=true. - When multiple domains return available, prioritize shorter names and .com over alternatives when presenting results. - If all checked domains come back registered, this is useful signal in itself — the namespace is saturated for that keyword pattern.

Check how many TLDs have specific keywords registered. Batch-compare keyword popularity by cross-TLD registration distribution. Best practices: - Use comma-separated keywords for side-by-side comparison (max 10): keywords='ai,tech,cloud,smart'. This is the tool's core strength — comparing relative popularity across multiple keywords in one call. - Interpreting total count: 100+ TLDs registered = highly competitive, well-known keyword. 50-100 = moderate popularity. 20-50 = niche but recognized. <20 = low market interest or very new concept. - The popular vs cctld vs other breakdown reveals the keyword's reach: high popular count (com/net/org/io/ai) = commercially validated. High cctld count = global brand interest or defensive registration. High other count = speculative gTLD registrations. - Use this to compare synonyms or variations before deciding which keyword to invest in — e.g., compare 'automate' vs 'automation' vs 'autoflow' to see which has stronger market validation. - Pairs well with tld_check for drilling into a single keyword's full TLD-by-TLD breakdown after identifying winners here.

Search domains that have completed the deletion cycle and are open for immediate registration at standard cost — no auction or backorder needed. These are the highest-value finds: domains with history available at regular price. Best practices: - Always use no_hyphen=true and no_number=true unless the user specifically wants them — the vast majority of hyphenated and numeric deleted domains are low-quality. - keyword defaults to 'contain' matching (substring), producing false positives (e.g., 'agent' matches 'magenta'). Use position=start or position=end for precise results. - sort=age_desc surfaces domains with the longest history first — a 20+ year old deleted .com at standard registration cost is a rare find worth highlighting. - sort=tld_counter_desc finds keywords popular across TLDs — if prefix_tld_count is high (20+) and the .com just dropped, that is notable. - For brandable names: combine length=5-10, type=all_alpha, no_hyphen=true, no_number=true. - hold=no_hold filters out domains still under registry hold that cannot yet be registered. - register_url links to Dynadot (affiliate). Disclose when presenting to users.

Query DNS records for a domain. Returns A, AAAA, MX, NS, TXT, CNAME, SOA. Key signals: MX present = active email. NS pointing to marketplace (Sedo, Afternic) = parked/for-sale. TXT with SPF/DKIM = active operations. No records at all = unconfigured/abandoned.

Monitor changes to premium .com domains in the past 7 days. The monitored pool consists of short-character .com domains (typically 1-4 letters) and high-value English single-word and two-word .com domains. This is not a general domain monitor — it specifically tracks the most valuable segment of the .com namespace. Change types: - Domain Transfer: Registrar changed — indicates ownership or management change. Report the old and new registrar as facts. Do not assume the reason (could be a sale, corporate restructuring, registrar migration, or portfolio consolidation). - Domain Expired: Domain entered expiration cycle. Report the fact. Do not characterize rarity or value unless verified with additional data. - New Registration: A previously unregistered premium name was registered. - Nameserver Change: NS records updated. An NS change to a domain marketplace (e.g., sedo.com, afternic.com, thisdomain.forsale) is a possible sale signal but not a certainty — report the old and new NS as facts. Best practices: - date_range=1d for last 24 hours, 3d for last 72 hours, all for full 7-day window (default). - length=1-3 or length=4 focuses on the shortest, most premium domains. - reason filters to a specific change type — use 'Domain Transfer' or 'Domain Expired' for the most newsworthy events. - sort=length_asc surfaces the shortest (most valuable) domains first. - has_digit=false filters to letter-only domains for higher quality results. - All interpretations must be evidence-based. Report what changed, not why. If the user wants to understand the reason behind a change, suggest whois or web_search to investigate further.