For developers · MCP / API

Product discovery for AI agents.

Cheap, reliable, hallucination-free product discovery for the agents you're building. One MCP/API call turns shopping intent into real, in-stock products, with live prices and working merchant links.

Soon also on
Difyn8nPipedream
run_shopping_discovery
200 OK
prompt ▸ ""

Example output · hover to pause, or pick an answer_type

MCP / API live
Integrate today
Paste-ready agent reply
suggested_agent_reply
Honest by default
match_quality + caveats
No checkout, ever
Merchant links only
Built for agents

Use Periskop through MCP or REST.

Connect the MCP server to Claude Code, Cursor, and other ChatGPT-compatible or custom agent runtimes, or call the REST endpoint from any app backend. Keys, usage, billing, docs, and OpenAPI live in the developer portal.

MCP for agents
// MCP, Claude Code, Cursor, custom agent runtimes
{
  "mcpServers": {
    "periskop": {
      "url": "https://mcp.periskop.ai",
      "headers": { "Authorization": "Bearer dp_..." }
    }
  }
}
In the developer portal
API keysUsageBillingDocsOpenAPI

Create a project, mint a key, and call run_shopping_discovery. Every result carries a result_id, re-fetch it with get_discovery_result.

Works with

Drop Periskop into your existing automation stack, native steps for Dify, n8n, and Pipedream.

Difyn8nPipedream
The runtime tax

Search returns links. Periskop returns the right products.

A generic agent searches, opens page after page, and re-reads it with an LLM on every request, slow, token-heavy, unreliable. Periskop returns the products in one structured call, with a paste-ready reply your agent renders directly.

Without Periskopevery request
prompt ▸ ""
01web_search×1· no strong matchcost
02open page· stale / out of stockcost
03web_search· broaden terms · still thincost
04open page×1· 404 · dead linkcost
05llm reads it all· reads everythingcost
Latency
unpredictable
Reliability
low ↓
still no reliable product
With Periskop · one call
prompt ▸ "cabin bag that fits Ryanair's size limit, under €60"
run_shopping_discovery→ 200 OK
answer_type recommendation · summary 2 in-stock picks within 40×20×25cm
  • Cabin Max Metz (40×20×25)amazon.frEUR 39.99
  • Aerolite Ryanair Cabin Bagdecathlon.frEUR 27.99
suggested_agent_reply

Two cabin bags under €60 that fit Ryanair's 40×20×25 cm limit: the Cabin Max Metz (€39.99) and the Aerolite Ryanair bag (€27.99), both in stock. Want the cheaper one, or a hard-shell option?

next_actionsCheaperHard-shell only
Latency
one call
Reliability
high ↑
ranked, in-stock, linked, ready to show
Swipe to compare →
Same retrieval, ranking, and validation, run once, ahead of time, not re-derived on every request.
Quality-gated supply

Onboarded does not mean trusted.

Periskop validates store structure, product extraction, price readability, link validity, image presence, and stability before a store can influence recommendations. Stores earn the right to shape recommendations.

1 · Store attempted
  • Accessible
  • Product pages found
  • Product cards detected
2 · Validated by Periskop
  • Product extraction
  • Price readability
  • Link validity
  • Image presence
  • Stability / latency
3 · Allowed use
  • Trusted, can shape best picks
  • Limited, alternatives or restricted contexts
  • Rejected, cannot influence recommendations
Validated, discovery-ready merchant supply is what makes agent recommendations safer.
The layer that was missing

Checkout was always solved. Knowing what to buy wasn't, until Periskop.

Payments, carts, and fulfillment already have a hundred providers, that part was never the problem. The unanswered question is the valuable one: out of everything for sale, what should your agent actually recommend? Periskop is that layer. It finds the right in-stock products and hands off a clean merchant link; your existing rails do the rest.

The hard part nobody solved, Periskop
  • Intent understanding
  • Retrieval
  • Ranking
  • Alternatives
  • Bundles
  • Caveats
  • Match quality
  • Merchant links
The easy part, already solved

Stripe · merchants · your storefront

  • Checkout
  • Payments
  • Orders
  • Fulfillment
  • Returns
Built for agents

One call. Build whatever needs live products and prices.

The same run_shopping_discovery call powers a chat assistant, a computer-use agent, a price-monitoring bot, an arbitrage scanner, a procurement workflow, a commerce copilot, a whole shopping app, and whatever you imagine next. You ship the experience; Periskop is the one call underneath.

One call · imagination is the limit
+…and whatever you ship next
AI shopping assistants

Real, in-stock picks dropped straight into chat, ranked, priced, and linked.

wireless earbuds under €50, good for running
Two solid picks under €50, both sweat-resistant:
JBL Wave Buds
amazon.fr
€34.99
open
Anker Soundcore P20i
fnac
€29.99
open
ranked from 40+ in-stock · live prices
Usage-based · €7 / 1,000 shopping requests · free credits on your first keySee pricing →
Build with Periskop

Product discovery for the agents you are building.

For AI shopping assistants, browser and computer-use agents, procurement workflows, commerce copilots, recommendation systems, and AI-native shopping apps.

FAQ

Common questions

What is Periskop?+

Periskop is product discovery for AI agents. One MCP/API call turns a shopping request into real, in-stock products, with live prices, working merchant links, alternatives, inferred bundles, caveats, a paste-ready reply, and a result_id, so your agent can recommend instead of crawling the web on every request.

Who is this for?+

Developers building AI shopping assistants, browser and computer-use agents, procurement and ops workflows, commerce copilots, recommendation features, accessibility shopping, and AI-native shopping apps.

How does it work?+

You send a prompt to run_shopping_discovery over MCP or REST. Periskop retrieves and ranks across quality-gated merchants and returns a structured response, items or an inferred bundle, plus a paste-ready suggested_agent_reply and next_actions, your agent renders directly. No per-site browsing, no runtime scraping.

Do merchants need to integrate?+

No. Periskop validates store structure, extraction, prices, links, images, and stability so only quality-gated, discovery-ready supply can influence results. Merchants don't lift a finger.

Is this just search?+

No. Search returns links you still have to open and reason over. Periskop returns the products themselves, ranked, in-stock, priced, and linked, in one call, with match_quality and caveats.

Do you handle checkout or carts?+

No. No checkout, no payments, merchant links only. Periskop never buys, places orders, or creates merchant checkout carts. Users complete purchases on merchant sites.

What happens when no good product exists?+

Periskop marks items match_quality: null and returns caveats rather than a forced or hallucinated pick, plus the closest matches and alternatives. Every result carries a result_id, so you can re-fetch it later with get_discovery_result.

What is the MCP/API?+

An MCP server for agent runtimes (Claude Code, Cursor, custom agents) and a REST endpoint for app backends. Keys, usage, billing, docs, and OpenAPI live in the developer portal.

How does pricing work?+

Usage-based: €7 per 1,000 shopping requests, with free credits on your first API key. Early access is founder-led onboarding.