AirShelf Catalog

Cross-vendor B2B catalog for AI agents: search, compare, find equivalents, request a quote.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Cross-vendor B2B catalog for AI agents: search, compare, find equivalents, request a quote.

    How to connect

    How to connect AirShelf Catalog to Claude

    The server address to paste into Claude settings:

    https://mcp.airshelf.ai/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect AirShelf Catalog to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.airshelf.ai/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect AirShelf Catalog to Cursor

    The server address to paste into Cursor settings:

    https://mcp.airshelf.ai/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (8)

    Raw names from tools/list. Only developers need these.

    search_catalogSearch the AirShelf cross-vendor product catalog by natural-language query. The catalog covers industrial-automation components (sensors, encoders, vacuum handling, motors and drives, circuit protection, machine vision — the largest category by row count), wiring devices (plugs, receptacles, connector bodies, rocker switches), multifunction printers (mfp), barcode printers, laser printers, mechanical keyboards, cybersecurity products, and threat-intelligence platforms. Industrial-automation and wiring-device rows are indexed by manufacturer part number, so a brand or part number in the query ("Pepperl+Fuchs retroreflective sensor", "IN5409") retrieves more reliably than a bare product type; those rows carry no normalized spec facets, so the `specs` filter does not apply to them. Returns ranked products with prices, specs, and per-row match accounting. Each row includes `unverified_specs`, the normalized spec names that lack claim-level receipts; never use those as decisive facts. Example queries: "tactile mechanical keyboard under $150", "Toshiba A3 colour multifunction device", "industrial barcode printer for a warehouse", "threat-intelligence platform with dark-web monitoring". Result fields: • canonical_name — the exact catalog name of the product. • spec_absence_note — spec fields absent from this product's golden record (AirShelf's verified product record); null when nothing is missing. • constraint_match_score and matched_criteria — query constraints supported by claim-level receipts. unverified_criteria names matching catalog values that still need confirmation; missing_criteria names values that are absent or conflict. • parsed.price_availability — all_null = true means every returned price is null. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error; query_had_budget reports whether the query carried one. • result.commercial_data — branch on actionable before using price or stock. Observations older than 24 hours ar
    find_productsDiscover candidate products for a buyer need. Takes a need in natural language (e.g. "best value home espresso machine", market "TH"), checks the verified catalog first, then uses live web discovery only when the catalog has no candidates. Returns up to 3 candidates with explicit fit accounting. find_products is the quick candidate-list tool; research_shopping is the full verified-research job. For a specific brand+model, search_catalog is cheaper and returns the same live-lookup block on a miss. Response fields: • candidates[].verification — "catalog-candidate" for a catalog starting point whose fit still needs checking, or "live-unverified" for a live page read during this run. • candidates[].status — "resolved" means both identity and the parsed buyer constraints were supported by the cited page; "abstain" means identity or need fit could not be established. Inspect constraint_check for matched, conflicting, and unverified requirements. • candidates[].constraint_check.receipts maps each receipt-backed matched requirement to its supporting source URL and trust label. • Candidates come from current web-search results, so they are a sample of what the market offers rather than a ranking. • status at the top level — "no_match" means discovery ran but no candidate was confirmed as satisfying the need; "disabled", "rate_limited", or "unavailable" means no discovery ran. • live_discovery.status="unavailable" means receipted catalog candidates were returned while live discovery was unavailable. Optional `market` (ISO 3166-1 alpha-2) biases discovery and marketplace checks toward seller pages serving that country and scopes the lookup cache. "Available in <market>" means the seller page serves that market, not that stock is guaranteed.
    research_shoppingresearch_shopping is the full verified-research job; find_products is the quick candidate-list tool. It runs as a background job and returns status "running" with a research ID while the minutes-long research continues; the same research ID returns the run on later polls until completion. Unsafe medical, legal, financial-advice, and professional-service asks return status "refused" before any work is queued. Completed runs return a researched recommendation with per-claim source receipts, or an explicit refusal when evidence is insufficient. Missing decision details return clarification questions before research starts. `market` biases discovery and marketplace checks toward seller pages serving that country; "available in <market>" means the seller page serves that market, not that stock is guaranteed. Example answer keys include {"budget":"500 USD","market":"US","category":"espresso machine"}.
    get_productGet the full golden record (AirShelf's verified product record) and latest price for one catalog product by slug ("<manufacturer>-<model>"). Returns the product's specs and provenance (which page each fact came from), plus canonical_name (its exact catalog name). A field's evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. Branch on commercial_data.actionable before using price or stock: observations older than 24 hours are withheld from latestPrice and retained only as labelled last_observed history. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error. In clients that render MCP Apps the response also draws one product card per call. related_products — relationships extracted from vendor documents (e.g. compatible toner or drum accessories with their source quotes, functional equivalents, supersessions); each entry names the related catalog slug, the relation type, its direction (direction is "from_this" when the relation reads this-product → related-product, "to_this" when it reads related-product → this-product), and the source URL and quote the relation was extracted from.
    compare_productsCompare 2-10 catalog products side-by-side on their datasheet specs. Slugs come from search_catalog and are case-insensitive and dash-tolerant ("e-STUDIO 331AC", "toshiba-e-studio-331ac" and "e-studio331ac" all resolve to the same product). Returns one item per product with canonical_name and spec_absence_note (spec fields absent from that product's golden record, AirShelf's verified product record). Branch on each item's commercial_data.actionable before using price or stock; stale observations are withheld from action fields. A slug that does not resolve comes back as not_found with a did_you_mean suggestion. The `provenance` option adds the source page and source type already stored with each fact.
    explain_productExplain the evidence behind a catalog row. Returns stored processing stages when available and always returns a golden-record field summary with source coverage. A field's evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. record.scraped_at is the catalog row's scrape time, not a per-claim evidence capture time.
    list_merchantsList public AirShelf merchants that have an assigned slug and at least one active product. Internal/demo and empty catalogs are excluded. Returns each merchant's name, slug, and product count; the slug is the `merchant` argument for request_quote.
    request_quoteSend a quote request for catalog products to a merchant's sales team on behalf of a named buyer. This is a two-step, double opt-in flow. The first call emails a confirmation link to `contact.email` and returns status "confirmation_required"; no lead exists and no merchant is contacted until the buyer confirms. A later call with the same arguments reports "awaiting_confirmation" while the email is unconfirmed, or "received" with a reference_number after confirmation. Merchant slugs come from list_merchants. Network-catalog brands that are absent from that list use merchant:"airshelf-network" with brandSlug:"<manufacturer-slug>"; AirShelf routes the confirmed request to that brand.