com.tacostreetlocating.ai/taco-street-locating

Est-ce que com.tacostreetlocating.ai/taco-street-locating est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.tacostreetlocating.ai/taco-street-locating » 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 9 outils

• ask_a_locator≈ 444 tokens

  Ask a question only a human can answer — current specials, real availability, lease flexibility, 'is the pool actually open'. A human locator replies during Central Time business hours, usually within a few hours. STRONGLY include the renter's contact with consent so the locator can follow up directly (agent sessions end; polling alone can strand an answer). Returns a question_id for check_answer as a bonus channel. Rate limited; batch related questions into one. Answers are point-in-time facts.

  Paramètres, retour & exemple (5)

  Paramètres

  • city · string · optionnel
    Metro the question concerns.
  • agent · string · optionnel
    Name of the referring assistant/product.
  • contact · string · optionnel
    The renter's phone/email, supplied with their consent. Strongly recommended; otherwise immediately share contact_capture_url returned by this tool.
  • question · string · requis
    The question for the human locator — specifics beat generalities.
  • apartments · array · optionnel
    Buildings the question is about.

  Exemple d'appel

  {"name": "ask_a_locator", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "guidance": "texte", "next_step": "texte", "question_id": "texte", "contact_status": "contactable", "contact_capture_url": "texte"}}

• check_answer≈ 224 tokens

  Poll the answer to an ask_a_locator question by question_id.

  Paramètres, retour & exemple (1)

  Paramètres

  • question_id · string · requis
    The id returned by ask_a_locator.

  Exemple d'appel

  {"name": "check_answer", "arguments": {"question_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "answer": "texte", "status": "open", "guidance": "texte", "question": "texte", "answered_at": "texte", "question_id": "texte", "contact_note": "texte", "contact_capture_url": "texte"}}

• create_shortlist≈ 310 tokens

  Turn finalist apartments into a Taco Street link (/my-list?s=...) that opens the renter's saved list with those buildings added — compare, AI Read, and free tour requests live there. Use the EXACT names returned by search_apartments.

  Paramètres, retour & exemple (3)

  Paramètres

  • city · string · optionnel · Austin | Dallas | Houston | San Antonio
    Metro, to disambiguate same-named buildings.
  • agent · string · optionnel
    Name of the referring assistant/product.
  • apartment_names · array · requis
    Exact building names from search_apartments to save to the renter's list.

  Exemple d'appel

  {"name": "create_shortlist", "arguments": {"apartment_names": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "note": "texte", "unmatched": [], "apartments": []}}

• get_apartment_details≈ 386 tokens

  Full fact sheet for one building: floorplan-level pricing with as-of dates, move-in costs (admin/application/parking/pet fees), last-known specials (dated — treat as last-known, not current), amenities, walkability, virtual tour. Use the EXACT name from search_apartments. Compute totals yourself from components; a free human locator confirms live numbers.

  Paramètres, retour & exemple (2)

  Paramètres

  • city · string · optionnel · Austin | Dallas | Houston | San Antonio
    Metro, to disambiguate same-named buildings.
  • name · string · requis
    Exact building name from search_apartments.

  Exemple d'appel

  {"name": "get_apartment_details", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"city": "texte", "name": "texte", "pets": "texte", "address": "texte", "pricing": {}, "building": {}, "guidance": "texte", "specials": {}, "neighborhood": "texte", "move_in_costs": {}, "lifestyle_tags": [], "taco_street_take": "texte"}}

• get_research_request≈ 298 tokens

  Use the private request key to retrieve progress and, after Alexander approves, the reviewed report snapshot. No draft, contact details or internal notes are returned. Do not share the key or continuation link publicly.

  Paramètres, retour & exemple (2)

  Paramètres

  • request_id · string · requis
    ID returned by request_apartment_research.
  • request_key · string · requis
    The original private request key.

  Exemple d'appel

  {"name": "get_research_request", "arguments": {"request_id": "texte", "request_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"report": {}, "status": "texte", "criteria": {}, "guidance": "texte", "duplicate": true, "apartments": [], "request_id": "texte", "continuation_url": "texte"}}

• request_apartment_research≈ 1020 tokens

  Submit a saved shortlist and renter brief to Taco Street with consent. Staff accepts the request before paid research starts; VAs verify gaps, then Alexander adds his judgment. Returns a private continuation link. No immediate report, guaranteed completion time, or tour booking. No email is sent by this tool.

  Paramètres, retour & exemple (15)

  Paramètres

  • city · string · requis
    Supported search market for this shortlist.
  • agent · string · optionnel
    Self-reported referring assistant or product; not a verified partner identity.
  • notes · string · optionnel
    Renter requirements and questions, not assistant-generated promises.
  • consent · boolean · requis
    True only after the renter agrees to share this brief and contact for research and follow-up.
  • contact · string · requis
    Renter's email or phone shared with consent for research follow-up.
  • move_in · string · requis
    Move-in month YYYY-MM or exact date YYYY-MM-DD. Never invent a day; confirm the year.
  • bedrooms · integer · requis
    Bedroom count, 0 for a studio, 1–4 otherwise.
  • budget_max · number · requis
    Monthly USD budget; specify its basis and flexibility separately.
  • client_name · string · requis
    Renter's name shared with consent.
  • request_key · string · requis
    Generate a fresh cryptographically random URL-safe key (at least 32 random bytes, 43 encoded characters). Keep it private. Reuse it only to retry this identical request and retrieve its status; a different brief needs a new key.
  • budget_basis · string · optionnel · base_rent | total_monthly | unknown
    base_rent, total_monthly, or unknown when the renter has not specified.
  • shortlist_token · string · requis
    The s parameter from the create_shortlist URL.
  • lease_term_months · ? · optionnel
    Requested lease length if known; omit when unknown.
  • budget_flexibility · string · optionnel · hard_max | target
    Defaults to target. Use hard_max only for an explicitly strict ceiling.
  • move_in_flexibility · string · optionnel · fixed | flexible
    Whether the move-in date is fixed or flexible.

  Exemple d'appel

  {"name": "request_apartment_research", "arguments": {"city": "texte", "consent": true, "contact": "texte", "move_in": "texte", "bedrooms": 1, "budget_max": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"report": {}, "status": "texte", "criteria": {}, "guidance": "texte", "duplicate": true, "apartments": [], "request_id": "texte", "continuation_url": "texte"}}

• request_locator_help≈ 441 tokens

  Hand the renter to Alexander, Taco Street's human locator, who confirms live pricing/availability and books tours — free to renters (properties pay locators). Follow-up arrives by TEXT or EMAIL, never a cold call. Requires the renter's real phone or email, shared with their consent. One request per renter — duplicates within 24h return the existing lead.

  Paramètres, retour & exemple (9)

  Paramètres

  • city · string · optionnel
    Metro the renter is searching (Austin, Dallas, Houston or San Antonio).
  • name · string · optionnel
    The renter's name, if shared.
  • note · string · optionnel
    Anything the locator should know.
  • agent · string · optionnel
    Name of the referring assistant/product.
  • contact · string · requis
    The renter's phone number or email (with their consent).
  • move_in · string · optionnel
    Move-in timeline, e.g. 'November'.
  • bedrooms · string · optionnel
    Bedroom count the renter needs, e.g. 1BR.
  • budget_max · integer · optionnel
    The renter's max monthly rent in USD.
  • neighborhoods · array · optionnel
    Neighborhoods the renter prefers.

  Exemple d'appel

  {"name": "request_locator_help", "arguments": {"contact": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"lead_id": "texte", "message": "texte", "success": true, "duplicate": true}}

• request_research_tours≈ 544 tokens

  After report approval and explicit renter consent, request human tour coordination for selected apartments. Include preferred dates, times and timezone in preferred_times. Uses the existing private research key and contact. One handoff per research report; identical retries return the existing request, changed preferences require staff follow-up. No appointment is booked or message sent.

  Paramètres, retour & exemple (5)

  Paramètres

  • consent · boolean · requis
    True only after the renter explicitly agrees to tour coordination using their saved contact.
  • request_id · string · requis
    ID of the approved research request.
  • request_key · string · requis
    Original private research access key. Never share publicly.
  • apartment_names · array · requis
    Exact apartment names from this report to discuss touring.
  • preferred_times · string · requis
    Renter-provided preferred dates, times and timezone; preferences are not confirmed appointments.

  Exemple d'appel

  {"name": "request_research_tours", "arguments": {"consent": true, "request_id": "texte", "request_key": "texte", "apartment_names": [], "preferred_times": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"report": {}, "status": "texte", "criteria": {}, "guidance": "texte", "duplicate": true, "apartments": [], "request_id": "texte", "continuation_url": "texte"}}

• search_apartments≈ 494 tokens

  Search Taco Street's curated apartment inventory in Austin, Dallas, Houston or San Antonio, TX. Returns scored matches with starting prices and a short 'why' per building. Use for long-term rentals only.

  Paramètres, retour & exemple (6)

  Paramètres

  • city · string · requis · Austin | Dallas | Houston | San Antonio
    Metro to search.
  • limit · integer · optionnel
    How many scored matches to return (1-10).
  • query · string · optionnel
    What the renter wants, in plain language (e.g. 'walkable, dog-friendly, near downtown').
  • bedrooms · string · optionnel · studio | 1BR | 2BR | 3BR | 4BR
    Bedroom count the renter needs.
  • budget_max · integer · optionnel
    Max monthly rent in USD.
  • neighborhoods · array · optionnel
    Preferred neighborhoods, if the renter named any.

  Exemple d'appel

  {"name": "search_apartments", "arguments": {"city": "Austin"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"city": "texte", "note": "texte", "count": 1, "apartments": []}}

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://ai.tacostreetlocating.com/mcp