ai.lendb/lendb

Est-ce que ai.lendb/lendb est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.lendb/lendb » 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 5 outils

• explain_specialty≈ 445 tokens

  Use this when someone asks what a mortgage loan type or borrower situation means, such as a DSCR loan, a bank statement loan, an ITIN loan, a non-warrantable condo or an FHA loan. Returns, for one specialty slug, what it is, why it can be hard to get done, the questions a borrower should ask a loan officer about it, its synonyms and a canonical_url.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    One of: condo, condo-non-warrantable, co-op, multi-family-2-4, manufactured, rural, new-construction, mixed-use, condotel, vacation-home, fha, va, usda, jumbo, non-qm, dscr, bank-statement, reverse, renovation, construction, heloc, down-payment-assistance, crypto-mortgage, self-employed, first-time-buyer, investor, refinance, permanent-resident, foreign-national, itin, low-credit, recent-credit-event, physician, 1099-income, asset-based

  Exemple d'appel

  {"name": "explain_specialty", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"slug": "texte", "label": "texte", "api_url": "texte", "category": "texte", "why_hard": "texte", "description": "texte", "canonical_url": "texte", "questions_to_ask": []}}

• find_loan_officers≈ 3198 tokens

  Use this when someone wants a US mortgage loan officer (or mortgage broker or lender contact) for a specific situation and place: for example an FHA, VA, USDA, jumbo, DSCR or ITIN loan, a first-time buyer, a self-employed borrower who needs a bank statement loan, a non-warrantable condo or a duplex, or a Spanish-speaking loan officer near a city, ZIP, region or state. Searches LenDb, an independent, lender-neutral database of US loan officers (coverage is partial), and returns a ranked list. Each result has the person's name, NMLS ID, lender, office location, distance_mi, reasons[], license_check for the property state (confirmed, lender_reported or federal_registration), match_status (exact, or partial with unconfirmed_specialties) and a canonical_url profile link. A city or ZIP keeps offices within 25 miles, widened to 50 or 100 when few are found (search.note); a state alone ranks statewide. Words like 'broker' or 'credit union' rank that kind of lender first. People with no license evidence for the state are listed separately in not_yet_verified. Also returns ambiguous_location when a city name fits several places, unassessed_requirements for parts of the situation LenDb cannot check, and citation_guidance. Phone numbers and email addresses are never returned.

  Paramètres, retour & exemple (6)

  Paramètres

  • debug · boolean · optionnel
    Also return how the query was parsed (debug.parsed, debug.filters). Default false.
  • limit · integer · optionnel
    Max results, default 10.
  • language · string · optionnel
    Language the borrower wants to be served in. Accepts an ISO 639-1 code ('es'), a BCP 47 tag ('es-MX', 'zh-TW'), an ISO 639-2/3 code ('spa'), an English name ('Spanish') or a native name ('español', '中文', '한국어', 'tiếng Việt'). A hard filter: every result speaks it. An unsupported language returns an error listing the supported codes (see list_specialties).
  • location · string · requis
    Where the property is: 'City, ST', a city, a 5-digit ZIP, a region ('Bay Area'), or a US state.
  • situation · string · requis
    The borrower's situation in plain words: property type, loan program, income type, credit, language, kind of lender. Example: 'duplex, self-employed, bank statement loan'.
  • fha_approved · boolean · optionnel
    Only loan officers whose current lender is FHA-approved per HUD's FHA Single Family Portfolio Snapshot data (the lender, not the person). Default false. Without it, an FHA search still ranks HUD-approved lenders' people first when all else is equal.

  Exemple d'appel

  {"name": "find_loan_officers", "arguments": {"location": "texte", "situation": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "debug": {}, "method": "texte", "notice": "texte", "sample": true, "search": {}, "related": {}, "results": [], "lender_level": {}, "canonical_url": "texte", "profile_match": {}, "fallback_applied": true}}

• get_lender≈ 548 tokens

  Use this when you need facts about a US mortgage lender, bank, credit union or mortgage broker company, by its company NMLS ID or by name (a partial name works). Returns the lender's type (bank, credit_union, imb, broker, other), headquarters state, website, the loan programs it offers (such as FHA, VA, jumbo or DSCR), program_approvals from agency data (FHA approval per HUD, with the month of loans it covers; absent means no HUD match on file, not that the lender lacks approval), activity (home loans it funded per HMDA, FFIEC/CFPB: counts by year, loan type and purpose, with as_of_year and source_url; cite it as 'HMDA, FFIEC/CFPB, <year>'; includes_brokered true means the counts include loans brokers originated; absent means no HMDA match on file, never that the lender makes no loans), how many of its loan officers LenDb lists, disciplinary_check, the date the record was last verified and a canonical_url.

  Paramètres, retour & exemple (1)

  Paramètres

  • nmls_id_or_name · string · requis
    Company NMLS ID (digits) or all or part of the company name.

  Exemple d'appel

  {"name": "get_lender", "arguments": {"nmls_id_or_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lender": {}, "notice": "texte", "sample": true, "canonical_url": "texte"}}

• get_loan_officer≈ 608 tokens

  Use this when you have a mortgage loan officer's individual NMLS ID and need their full profile. Returns LenDb's sourced record: name, title, current lender and branch, employment history, state licenses with license confidence, specialties (such as FHA, VA, bank statement or DSCR) with the evidence for each, languages spoken, stated experience, the earliest state license record, public links (such as their page on the lender's site), disciplinary_check ('not_checked' means LenDb has not yet checked regulator records), the date the record was last verified and a canonical_url. US only. Phone numbers and email addresses are not returned; the LenDb profile page shows them after a human check.

  Paramètres, retour & exemple (1)

  Paramètres

  • nmls_id · ? · requis
    Individual NMLS ID, digits only, e.g. 452476.

  Exemple d'appel

  {"name": "get_loan_officer", "arguments": {"nmls_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"notice": "texte", "sample": true, "loan_officer": {}, "canonical_url": "texte"}}

• list_specialties≈ 384 tokens

  Use this when you need the mortgage situations LenDb can match on. Returns every specialty with its slug, category (property type, loan program or borrower situation), label, one-line description and canonical_url: for example FHA, VA, USDA, jumbo, DSCR, bank statement, ITIN, self-employed, first-time buyer, non-warrantable condo, multi-family 2-4 units and reverse mortgage. Also returns the supported languages as ISO 639-1 codes with names.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_specialties", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"languages": {}, "specialties": [], "canonical_url": "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://lendb.ai/mcp