ai.klarix/intelligence

Est-ce que ai.klarix/intelligence est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.klarix/intelligence » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 15 outils

• analyze_head_to_head≈ 1700 tokens

  Compare YOUR company against a specific competitor or incumbent you want to displace. Researches both sides on the live public web, then returns asymmetric advantages (where you win structurally), their defensive moats (where to stop arguing), a fixed four-dimension comparison matrix (Pricing, Tech / Delivery Speed, Quality Floor, Support / Customization), spoken talk tracks and landmines for a live evaluation, and a three-step displacement strategy. Identify your side with our_domain, our_company_name, or a Klarix client_id. Any claimed advantage the evidence does not support is reported back rather than repeated.

  Paramètres, retour & exemple (8)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • target_domain · string · requis
    The competitor or incumbent vendor you are trying to displace, e.g. "zoominfo.com".
  • our_advantages · array · optionnel
    Advantages you believe you hold, in your words. Merged with our_differentiators; the analysis tests them against the evidence rather than accepting them.
  • target_vertical · string · optionnel
    The buying market this head-to-head is aimed at, e.g. "medical device OEMs". Sharpens every talk track.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • target_company_name · string · optionnel
    Proper name of the target, when the domain does not make it obvious.

  Exemple d'appel

  {"name": "analyze_head_to_head", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "verdict": "texte", "unknowns": [], "landmines": [], "our_domain": "texte", "our_context": {}, "talk_tracks": [], "their_moats": [], "win_posture": "texte", "figure_check": {}, "target_domain": "texte", "our_positioning": "texte"}}

• detect_account_triggers≈ 1202 tokens

  Detect recent account inflection points (leadership changes, funding, hiring surges, product updates, regulatory events) within a timeframe.

  Paramètres, retour & exemple (8)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • target_domain · string · requis
    Domain of the account to scan for inflection points, e.g. "acme.com".
  • timeframe_days · integer · optionnel
    How far back to look for triggers, in days. Default 90. Anything older is context, not a trigger.
  • target_vertical · string · optionnel
    The market this account operates in, e.g. "medical device OEMs". Sharpens which events count as triggers.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • target_company_name · string · optionnel
    Proper name of the account, when the domain does not make it obvious.

  Exemple d'appel

  {"name": "detect_account_triggers", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "our_context": {}, "scan_summary": "texte", "target_domain": "texte", "timeframe_days": 1, "target_vertical": "texte", "leadership_moves": [], "confidence_detail": "texte", "growth_and_hiring": [], "evidence_confidence": "texte", "product_and_pricing": []}}

• find_matched_prospects≈ 1743 tokens

  Build a first-pass candidate list from hundreds of thousands of pre-profiled B2B companies using Voyage 4 semantic vector embeddings. Ranks accounts by topical similarity to an ICP description, tech stack, business model, and vertical, then screens the retrieved candidates for buyer-vs-vendor role and corporate status and reports what it withheld. Returns a candidate net, not a qualified list: the similarity figure is not a fit score, and every account should go through score_prospect_fit before outreach.

  Paramètres, retour & exemple (17)

  Paramètres

  • limit · integer · optionnel
    Maximum prospects to return (1-25, default 10).
  • screen · boolean · optionnel
    Screen retrieved candidates for buyer-vs-vendor role and corporate status before returning them (default true). Set false for the raw similarity ranking, which will include companies that sell what the ICP describes.
  • vertical · string · optionnel
    Filter by vertical: "AI SaaS & DevTools", "Recruiting & Staffing", "Precision Manufacturing & Hardware", etc.
  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • countries · array · optionnel
    Restrict to accounts headquartered in these countries (matched against HQ location), e.g. ["United States", "Canada"].
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • revenue_max · number · optionnel
    Maximum annual revenue in USD. Recorded for downstream scoring; the semantic index carries no revenue field, so it does not narrow retrieval.
  • revenue_min · number · optionnel
    Minimum annual revenue in USD. Recorded for downstream scoring; the semantic index carries no revenue field, so it does not narrow retrieval.
  • icp_or_query · string · requis
    Target ICP description, search criteria, tech stack, or problem statement, e.g. "AI infrastructure companies serving enterprise ML teams with high GPU usage".
  • sub_category · string · optionnel
    Filter by sub-category, e.g. "Serverless GPU Cloud", "Executive Search", "Contract Manufacturing & EMS".
  • headcount_max · integer · optionnel
    Maximum employee headcount. Accounts whose headcount band starts above this are dropped.
  • headcount_min · integer · optionnel
    Minimum employee headcount. Accounts whose headcount band tops out below this are dropped.
  • required_tech · array · optionnel
    Require at least one of these technologies in the confirmed tech stack, e.g. ["CUDA", "PyTorch"].
  • min_similarity · number · optionnel
    Minimum vector cosine similarity threshold (0.0 - 1.0, default 0.35). Measures topical closeness to the ICP text, not fit or buying readiness.
  • exclude_domains · array · optionnel
    Domains to exclude from results (e.g. existing customers or disqualified accounts).
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.

  Exemple d'appel

  {"name": "find_matched_prospects", "arguments": {"icp_or_query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "screen": {}, "source": "texte", "vertical": "texte", "prospects": [], "our_context": {}, "total_matches": 1, "search_latency_ms": 1, "withheld_accounts": [], "index_last_updated": "texte", "qualification_status": "texte", "total_universe_indexed": 1}}

• generate_displacement_playbook≈ 1169 tokens

  Generate an end-to-end competitive displacement playbook with switching cost mitigations, POC blueprints, and migration timelines.

  Paramètres, retour & exemple (7)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • target_domain · string · requis
    The incumbent vendor you are displacing, e.g. "zoominfo.com".
  • account_domain · string · optionnel
    The account where the displacement happens, e.g. "acme.com". Supplying it grounds the plan in their environment instead of generic switching advice.
  • target_vertical · string · optionnel
    The market this displacement is aimed at, e.g. "medical device OEMs". Sharpens migration risk and executive framing.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.

  Exemple d'appel

  {"name": "generate_displacement_playbook", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "our_context": {}, "target_domain": "texte", "account_domain": "texte", "incumbent_name": "texte", "target_vertical": "texte", "confidence_detail": "texte", "executive_aircover": {}, "incumbent_lock_ins": [], "data_migration_plan": [], "displacement_thesis": "texte"}}

• generate_outreach_sequence≈ 784 tokens

  Write cold outreach that opens on a researched, dated insight about the prospect rather than a pleasantry. Supports a 3-step email sequence, a 3-step LinkedIn sequence, or 6 multivariant openers. Enforces the Klarix voice contract (banned AI words and phrases, punctuation tells, rhythm) and reports any violations. Writes to a job title, never to an individual, and never emits contact details.

  Paramètres, retour & exemple (5)

  Paramètres

  • channel · string · requis · email | linkedin | multivariant
    email = 3-step sequence, linkedin = connect + 2 follow-ups, multivariant = 3 competing openers per channel
  • value_prop · string · requis
    What you do for them, in your own words. Include the outcome and, if you have one, a number.
  • target_title · string · requis
    Job title or function you are writing to, e.g. "VP Revenue Operations". A title, never a person.
  • prospect_domain · string · optionnel
    Domain to research for the opening insight. Strongly recommended.
  • prospect_company · string · requis
    Company you are writing to

  Exemple d'appel

  {"name": "generate_outreach_sequence", "arguments": {"channel": "email", "value_prop": "texte", "target_title": "texte", "prospect_company": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"angle": "texte", "channel": "texte", "sources": [], "messages": [], "do_not_say": [], "voice_check": {}, "target_title": "texte", "anchor_source": "texte", "anchor_insight": "texte", "prospect_company": "texte", "confidence_detail": "texte", "evidence_confidence": "texte"}}

• generate_swot_analysis≈ 1462 tokens

  Deep multi-source web crawl into a four-quadrant SWOT matrix for a company: internal strengths (moat, proprietary tech, distribution lock) and weaknesses (pricing friction, customer complaints, legacy tech), plus external opportunities (untapped verticals, market vacancies, adjacent expansion) and threats (substitutes, price commoditization, regulatory shifts). Every entry carries evidence and a consequence. Adds strategic exploit vectors for winning deals against them and defensive counter-plays. Curate it to your own business with our_company_name, our_domain, our_differentiators, or a Klarix client_id so every vector is one you can actually execute. Returns markdown plus structured JSON.

  Paramètres, retour & exemple (8)

  Paramètres

  • domain · string · requis
    Company web domain to analyze, e.g. "zoominfo.com"
  • vertical · string · optionnel
    Vertical to sharpen the analysis against, e.g. "lithium battery manufacturers".
  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • company_name · string · optionnel
    Proper company name, if the domain does not make it obvious. Improves search precision.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • competitor_viewpoint · boolean · optionnel
    Override the derived relationship. Left unset, the tool works out whether you actually compete with this company from your own business context and only then adds exploit vectors. Set true to force competitive framing, false to force a self-assessment or partner review.

  Exemple d'appel

  {"name": "generate_swot_analysis", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"swot": {}, "domain": "texte", "sources": [], "category": "texte", "unknowns": [], "vertical": "texte", "our_context": {}, "company_name": "texte", "relationship": "texte", "confidence_detail": "texte", "evidence_confidence": "texte", "competitor_viewpoint": true}}

• get_buying_committee≈ 1286 tokens

  Map the internal buying committee (Economic Buyer, Champion, Technical Evaluator, Procurement) for an account with title patterns, pain points, objections, and multi-threading strategy.

  Paramètres, retour & exemple (7)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • target_domain · string · requis
    Domain of the account whose buying committee you need to map, e.g. "acme.com".
  • target_vertical · string · optionnel
    The market this account operates in, e.g. "medical device OEMs". Sharpens titles, pains, and objections.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • target_company_name · string · optionnel
    Proper name of the account, when the domain does not make it obvious.

  Exemple d'appel

  {"name": "get_buying_committee", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "our_context": {}, "target_domain": "texte", "economic_buyer": {}, "target_vertical": "texte", "committee_summary": "texte", "confidence_detail": "texte", "procurement_legal": {}, "technical_champion": {}, "evidence_confidence": "texte", "target_company_name": "texte"}}

• get_company_intelligence≈ 722 tokens

  Synthesize an executive one-pager on a company from live public web sources: snapshot, findings per requested focus area, dated buying signals, deal risks, and stated unknowns. Every claim carries a source URL. Focus areas include pricing, leadership (roles only), recent_events, tech_stack, customers, hiring, funding, products, and risks.

  Paramètres, retour & exemple (2)

  Paramètres

  • domain · string · requis
    Company web domain, e.g. "acme.com"
  • focus_areas · array · optionnel
    Which angles to dig into. Defaults to overview, recent_events, products, risks. "leadership" covers roles, org structure, and publicly reported executive names — never contact details.

  Exemple d'appel

  {"name": "get_company_intelligence", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"risks": [], "domain": "texte", "sources": [], "snapshot": {}, "unknowns": [], "focus_areas": [], "company_name": "texte", "buying_signals": [], "focus_sections": [], "confidence_detail": "texte", "executive_summary": "texte", "evidence_confidence": "texte"}}

• get_competitor_battlecard≈ 1149 tokens

  Build a live sales battlecard for a competitor domain: SWOT from their point of view, the gap between their marketing claims and buyer-reported reality, and concrete landmines with spoken talk tracks. Every claim cites a public source. Optionally aim it at a target vertical, and curate it to your own business by passing our_company_name, our_domain, our_differentiators, or a Klarix client_id — landmines and talk tracks then become lines your seller can actually defend.

  Paramètres, retour & exemple (6)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • target_vertical · string · optionnel
    Vertical the battlecard should be aimed at, e.g. "staffing agencies". Sharpens the talk tracks.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • competitor_domain · string · requis
    Competitor web domain, e.g. "zoominfo.com"
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.

  Exemple d'appel

  {"name": "get_competitor_battlecard", "arguments": {"competitor_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"swot": {}, "sources": [], "category": "texte", "landmines": [], "our_context": {}, "relationship": "texte", "target_buyer": "texte", "trap_questions": [], "where_they_win": [], "competitor_name": "texte", "pricing_posture": "texte", "target_vertical": "texte"}}

• get_deep_research≈ 1054 tokens

  Exhaustive intelligence probe on a company across five dimensions: firmographic and corporate evolution (funding, revenue tier, team growth), product and technology teardown (stack, API presence, core capabilities), leadership and organizational signals (executive hires, board composition, departures — publicly reported executive names allowed when cited, never contact details), active buying and growth triggers (hiring surges, expansion, product launches), and risk analysis with explicit unknowns. Every finding carries a source citation and an implication. Defaults to depth "standard", which returns a tighter, higher-quality citation list; request "comprehensive" when maximum coverage matters more than citation density.

  Paramètres, retour & exemple (3)

  Paramètres

  • depth · string · optionnel · standard | comprehensive
    "standard" (default) probes all five dimensions with one lead query each and a 12-source budget. It concentrates the source budget on the highest-quality result per dimension, which in practice yields a cleaner citation list. "comprehensive" fans out to 14 queries and a 24-source budget; use it when you need maximum coverage and can accept more marginal sources in the citation list.
  • domain · string · requis
    Company web domain, e.g. "acme.com"
  • focus_topics · array · optionnel
    Extra angles to probe, e.g. ["thermal management patents", "EU expansion"]. Added to the standard probe, not a replacement for it.

  Exemple d'appel

  {"name": "get_deep_research", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"depth": "texte", "risks": [], "domain": "texte", "sources": [], "snapshot": {}, "dimensions": [], "company_name": "texte", "focus_topics": [], "buying_triggers": [], "confidence_detail": "texte", "executive_summary": "texte", "explicit_unknowns": []}}

• get_market_landscape≈ 1030 tokens

  Map a competitive landscape for an industry or vertical from live public sources: Tier-1 incumbents against emerging disruptors, category positioning quadrants with the white space in each, published pricing models and price bands, and the narrative themes that dominate zero-click and AI answers — including which themes are still open. Ends with buyer shifts and defensible entry wedges. Returns a landscape matrix in markdown plus structured JSON.

  Paramètres, retour & exemple (3)

  Paramètres

  • target_geo · string · optionnel
    Geography to scope the map to. Default "US / Global".
  • industry_or_vertical · string · requis
    Market to map, e.g. "lithium battery manufacturing" or "b2b sales intelligence".
  • include_pricing_benchmarks · boolean · optionnel
    True (default) researches published pricing models and price bands. False skips the pricing queries for a faster map.

  Exemple d'appel

  {"name": "get_market_landscape", "arguments": {"industry_or_vertical": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "target_geo": "texte", "market_name": "texte", "buyer_shifts": [], "entry_wedges": [], "pricing_models": [], "market_maturity": "texte", "narrative_themes": [], "confidence_detail": "texte", "market_definition": "texte", "tier_1_incumbents": []}}

• score_prospect_fit≈ 1188 tokens

  Score a company against your ICP on five weighted axes — Strategic Fit, Tech Alignment, Buyer Persona Readiness, Growth Triggers, and Landmine Risk — each 1-10, with a weighted overall and a 7+/10 pursue threshold. Uses live public web evidence and cites every claim. Curate the score to your own business with our_company_name, our_domain, our_differentiators, or a Klarix client_id — a client_id also supplies the ICP, so icp_description becomes optional. Judges roles, never individuals; returns no contact details.

  Paramètres, retour & exemple (9)

  Paramètres

  • domain · string · requis
    Primary web domain, e.g. "acme.com"
  • vertical · string · optionnel
    Vertical to judge fit within, e.g. "industrial manufacturing"
  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • company_name · string · requis
    Legal or trading name of the prospect company
  • icp_description · string · optionnel
    Your ideal customer profile in plain language: segment, size, the problem you solve, and who buys. A vague ICP produces a vague score. Optional only when client_id resolves to a context file that already carries an ICP.
  • ideal_tech_stack · array · optionnel
    Tools or platforms that signal a good technical fit, e.g. ["Snowflake", "Salesforce", "dbt"]
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.

  Exemple d'appel

  {"name": "score_prospect_fit", "arguments": {"domain": "texte", "company_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": [], "domain": "texte", "sources": [], "headline": "texte", "landmines": [], "threshold": 1, "icp_source": "texte", "our_context": {}, "company_name": "texte", "disqualifiers": [], "overall_score": 1, "confirmed_tech": []}}

• search_scientific_evidence≈ 680 tokens

  Retrieve verifiable academic and engineering literature for a technical topic so a claim can cite a resolvable DOI instead of a vendor blog post. Queries Semantic Scholar (citation graph, abstracts, open-access PDFs) and the arXiv preprint index, merges duplicates, and ranks by citation count then recency. Returns title, authors, year, DOI / arXiv URL, citation count, and an extractive key finding taken verbatim from the abstract. Keyless; set SEMANTIC_SCHOLAR_API_KEY to escape the shared anonymous rate limit.

  Paramètres, retour & exemple (4)

  Paramètres

  • topic · string · requis
    Technical topic phrase, e.g. "battery cathode thermal runaway" or "vector database latency". Noun phrases beat questions.
  • source · string · optionnel · all | semantic_scholar | arxiv | pubmed
    Which index to query. Default "all" merges Semantic Scholar, arXiv, and PubMed (clinical/biotech) and dedupes by DOI / PMID / arXiv id / title.
  • year_from · integer · optionnel
    Publication-year floor. Papers older than this, and papers with no known year, are dropped.
  • max_results · integer · optionnel
    Papers to return. Default 5.

  Exemple d'appel

  {"name": "search_scientific_evidence", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"topic": "texte", "papers": [], "source": "texte", "paper_count": 1, "provider_notes": [], "providers_queried": []}}

• teardown_product_spec≈ 1311 tokens

  Deconstruct a physical hardware device, battery pack, medical system, or software API into an institutional-grade technical specification table with exact units, tolerances, verified images/diagrams, datasheet links, certifications, and displacement seams.

  Paramètres, retour & exemple (10)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • spec_category · string · optionnel · all | hardware_device | software_api | medical_clinical | battery_energy | materials_machining
    Focus category for specification extraction. Defaults to "all".
  • target_domain · string · requis
    Domain of the company whose product you want deconstructed, e.g. "tesla.com", "enphase.com", or "zoominfo.com".
  • target_vertical · string · optionnel
    The target market context (e.g., "custom robotics OEMs" or "sales tech").
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_product_specs · array · optionnel
    Our own product specifications to benchmark against their specs to highlight asymmetric displacement seams.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • target_company_name · string · optionnel
    Proper name of the company, when domain alone is ambiguous.
  • product_name_or_model · string · optionnel
    Specific product name, model number, or SKU to analyze (e.g., "Megapack-2XL" or "Enrich API"). If omitted, analyzes their flagship offering.

  Exemple d'appel

  {"name": "teardown_product_spec", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "our_context": {}, "product_name": "texte", "spec_summary": "texte", "image_caption": "texte", "target_domain": "texte", "datasheet_urls": [], "specifications": [], "target_vertical": "texte", "model_or_version": "texte", "confidence_detail": "texte"}}

• teardown_tech_stack≈ 1272 tokens

  Deconstruct an account's technical infrastructure, dev tools, cloud providers, AI/data stack, and identify displacement vulnerabilities.

  Paramètres, retour & exemple (8)

  Paramètres

  • client_id · string · optionnel
    Klarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
  • our_domain · string · optionnel
    Your own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
  • focus_areas · array · optionnel
    Layers to probe. Defaults to all five: frontend_backend, cloud_infra, data_ai, business_tools, security.
  • target_domain · string · requis
    Domain of the account whose stack you want deconstructed, e.g. "acme.com".
  • target_vertical · string · optionnel
    The market this account operates in, e.g. "medical device OEMs". Sharpens which stack gaps matter.
  • our_company_name · string · optionnel
    Your company name. Curates the analysis toward how YOU win instead of a generic read.
  • our_differentiators · array · optionnel
    What you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
  • target_company_name · string · optionnel
    Proper name of the account, when the domain does not make it obvious.

  Exemple d'appel

  {"name": "teardown_tech_stack", "arguments": {"target_domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"sources": [], "unknowns": [], "cloud_infra": [], "focus_areas": [], "our_context": {}, "stack_summary": "texte", "target_domain": "texte", "target_vertical": "texte", "business_tooling": [], "confidence_detail": "texte", "data_and_ai_stack": [], "evidence_confidence": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.klarix.ai/mcp