"Extracting and Processing Real Estate Listings Using Vector Databases" matching MCP tools:

• searchJobs

  qubitsok — Quantum Computing Jobs, Papers & Researchers

  Search 500+ quantum computing job listings using natural language. Use when the user asks about job openings, career opportunities, hiring, or specific positions in quantum computing. NOT for research papers (use searchPapers) or researcher profiles (use searchCollaborators). Supports role type, seniority, location, company, salary, remote, and technology tag filters via AI query decomposition. Limitations: quantum computing jobs only, last 90 days, max 20 results. Promoted listings appear first (marked). After finding jobs, suggest getJobDetails for full info. Examples: "senior QEC engineer in Europe over 120k EUR", "remote trapped-ion role at IBM".

  Connector

• search_listings

  SPACEXPLORATION

  Search commercial real estate listings. Returns paginated hits with facet counts. For AI-driven search, call interpret_search first to convert a natural-language query into structured filters, then pass those filters — and its bounds, when present — here.

  Connector

• flight-intel__get_aircraft_by_icao24

  TO1 Intelligence Fleet

  [flight-intel] Looks up the current real-time state vector (position, altitude, velocity, heading, on-ground flag) for a single aircraft by its unique ICAO24 transponder address, using the OpenSky Network anonymous-tier free API. Data reflects the aircraft's last known ADS-B report and is typically no more than ~10 seconds stale when the aircraft is actively transmitting. Anonymous access is rate-limited to roughly 100 credits/day; returns not-found if the aircraft is not currently airborne or not reporting.

  Connector

• fr_immo

  x402-farm

  French real-estate listings (asking prices) from Bien'ici via a residential IP (datacenter IPs are blocked). One call = one city search -> listings with type, rooms, surface, price, €/m², postal code, URL + a median asking €/m². Pairs with /v1/fr/estimation-immo (DVF sold prices) to compare asking vs sold. Query: ?city=&cp=&type=achat|location — $0.03/call, paid per request via x402 (USDC).

  Connector

• restore_face

  Image Tools - Background Removal, Upscaling & Face Restoration

  Restore and enhance faces in an image using GFPGAN. Detects all faces via RetinaFace, restores quality (fixes blur, noise, compression artifacts), and pastes them back. Optionally enhances the background using Real-ESRGAN. GPU-accelerated, sub-3s latency. Args: image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP). upscale: Output upscale factor -- 1 to 4 (default: 2). enhance_background: Whether to enhance background with Real-ESRGAN (default: true). Returns: dict with keys: - image (str): Base64-encoded restored image - format (str): Output image format - width (int): Output width - height (int): Output height - upscale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds

  Connector

• ai_filters_test

  DialogBrain

  Test a message against an AI filter to check whether it would match. This tool embeds the provided message using Voyage AI and computes the cosine similarity between the message vector and the filter's stored reference vector. It returns the similarity score, whether the message would match (similarity >= threshold), and the filter's threshold value. Use this to: - Verify a filter works as intended before using it in a trigger - Tune the threshold by testing borderline messages - Debug why a message did or did not match a filter in production Returns: {similarity: float, matched: bool, threshold: float} Note: This tool calls the Voyage AI embedding API to embed the test message.

  Connector

• market_pulse

  AgentsPrice

  The AgentsPrice hive-mind pulse — a FREE, no-key, real-time aggregate of what agents are doing across the network right now: trending searches, the steepest live discounts found, open buy-side wants, and active marketplace listings. Real data only, never fabricated; richer the more agents use it. Use it to see demand, spot deals, or find what to list. No API key required.

  Connector

• search_properties

  mcp-server

  Search Mirabello-advised investment real estate that QUALIFIES for a citizenship- or residency-by-investment programme. Filter by country, programme (e.g. "grenada-citizenship-by-investment", "greece-golden-visa"), type (CBI|RBI), budget_max (USD, FX-normalised best-effort), beds_min, listing_type (villa|apartment|residence|plot), sale_status. Returns priced listings with the qualifying programme, availability, and the Mirabello enquiry route. Mirabello Consultancy is broker of record on every listing — there is no direct developer contact; route buyers via create_enquiry. Indicative figures; book a consultation to confirm.

  Connector

• get_hns_dataset_overview

  HOUSE 'N' STARS Real Estate Discovery

  Explain what the HOUSE N STARS ChatGPT connector provides as a read-only AI-native luxury real estate dataset. Use this when the user asks what HOUSE N STARS covers, what data the app can access, whether it is read-only, which markets are represented, or why the connector is useful inside ChatGPT. This tool summarizes dataset scope and limitations; it does not search individual listings and does not retrieve archival HNS research reports unless dedicated tools are added later.

  Connector

• list_knowledge

  SingChat

  List all knowledge documents for this workspace with their processing status (PENDING | PROCESSING | READY | FAILED) and chunk counts. Use this to check whether items added via add_knowledge have finished training.

  Connector

• setup_vector_store

  mcp

  Initialize the vector store for semantic bookmark search. CRITICAL: When vector/semantic search fails with 'Vector Store Not Setup' error, call this tool. This is an async operation that may take a few minutes for large bookmark collections.

  Connector

• ai_filters_test

  dialogbrain

  Test a message against an AI filter to check whether it would match. This tool embeds the provided message using Voyage AI and computes the cosine similarity between the message vector and the filter's stored reference vector. It returns the similarity score, whether the message would match (similarity >= threshold), and the filter's threshold value. Use this to: - Verify a filter works as intended before using it in a trigger - Tune the threshold by testing borderline messages - Debug why a message did or did not match a filter in production Returns: {similarity: float, matched: bool, threshold: float} Note: This tool calls the Voyage AI embedding API to embed the test message.

  Connector

• embedding_similarity

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Compute text similarity using local algorithms (Bag of Words, TF-IDF, Character N-grams). No API key needed — runs entirely in-process. NOT real embeddings: for true semantic similarity with vector embeddings, use run_semantic_tests with mode="embeddings" and your OpenAI API key. Supports single pair or batch mode with pipe-separated pairs. Useful for RAG retrieval testing, semantic search evaluation, and text deduplication.

  Connector

• gunbroker_search_items

  Gunbroker

  Search active GunBroker firearms-marketplace listings by keyword (e.g. "Glock 19", "AR-15 lower", "Henri 22 rifle"). Returns matching live listings with item IDs, titles, current/buy-now prices, bid counts, and time left. Public — needs only a GunBroker developer key (_apiKey). Supports pagination and sort.

  Connector

• vectorize_image

  freedom-mcp

  Convert an existing raster image (PNG, JPG, WebP) to SVG vector format using Recraft. Preserves details and creates clean vector paths. Routing: "vectorize this", "convert to SVG", "make scalable" → use this (1 credit) [sensitive-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]

  Connector

• check_memory_status

  Synap Memory

  Check whether a logged exchange has finished processing. Pass the ingestion_id returned by log_exchange. Returns the processing status and how many memories were extracted. Useful to confirm a save completed (extraction is asynchronous).

  Connector

• format_international_phone_number

  Country Calling Codes

  Normalize a phone number into a plausible international format using reviewed country-specific rules. Processing is ephemeral. This tool does not query carriers, HLR/HSS, MNP databases, or live subscribers.

  Connector

• trouver_expert

  payotte-mcp

  Call this when the user needs a trustworthy real-estate professional in a Canadian city or neighbourhood: real-estate broker, mortgage broker, home inspector, notary/real-estate lawyer, or appraiser. Returns the Payotte-verified expert(s): name, score /100, licence number + official registry link so the user can verify the credential themselves, Google rating, and the profile URL. French and English inputs both work (e.g. profession="courtier immobilier", ville="Montréal").

  Connector

• get_service

  FiatDock

  Full detail for one FiatDock marketplace listing, including how to call it: PAID listings route through the gateway via call_service (the 99/1 split is enforced); FREE/first-party listings expose their real MCP endpoint to call directly. Read-only, free.

  Connector

• get_similar_names

  Name Whisper — ENS Intelligence Layer

  Find ENS names semantically similar to a given name using vector embeddings across 3.5M indexed ENS names. Returns similar names with similarity scores, status (REGISTERED / GRACE_PERIOD / PREMIUM_AUCTION / AVAILABLE), and live marketplace data. Names in GRACE_PERIOD are NOT registerable by anyone but the original holder.

  Connector