SuggestAPI
SuggestAPI mengekspos alat-alat perdagangan melalui MCP dan WebMCP di Agent Gateway-nya.
Dokumentasi
Language
Search the site
Search SuggestAPI
Press Enter for the full results page. Shortcut: ⌘K / Ctrl+K.
After the citation
You have AEOAnswer engine optimization. The work of getting your business cited in an AI answer..Do you know how to get the conversion?
A citation puts you in the answer. It does not close the sale. SuggestAPI is the discovery layer that comes next: current items a person or an agent can actually buy, from the search you already run.
Start BuildingExplore live examplesWhat is AEO?
Works with the search you already run
Algolia · Typesense · Elasticsearch · Meilisearch · Shopify
The crawler delay
Google’s index is a delayed copy of your catalog.
A size 9 can sell out at noon and still look in stock in a search result. A citation names the merchant. A live query checks the price and the stock right now.
What changes
Make the search you already have understand the request.
Commerce, documentation, and industrial catalogs share one pattern. SuggestAPI turns a messy request into the constraints your existing search can use.
One use case
Commerce
“Hiking boots for Iceland in October under $250”
SuggestAPI reads
- → Destination
- → Season
- → Budget
- → Category
Docs and SaaS
Knowledge base
“How do I rotate a workspace API key?”
SuggestAPI reads
- → Product area
- → Task
- → Object
Industrial catalogs
Part numbers
“316SS 1/2 in valve, 3000 PSI”
SuggestAPI reads
- → Material
- → Size
- → Part type
- → Pressure
What SuggestAPI adds
- 01
Understand the request
Extract constraints from natural language, whether the record is a product, a document, or a part. 2. 02
Guide your existing search
Rewrite, route, filter, and rank requests for the engine already underneath. 3. 03
Keep context across the journey
Preserve the request when someone refines, compares, or asks a follow-up. 4. 04
Return results an app or agent can use
Hand back structured matches, not only a keyword string.
Why we built this
You shouldn’t need a new discovery layer for every assistant.
People search with messy, persistent requests. Existing search drops that context after one query. You shouldn’t have to rebuild discovery for every new app or assistant.
People, apps, and agents reach SuggestAPI first. SuggestAPI understands the request and keeps that context. Your existing search finds and ranks records. Your application takes the next step.
People, apps, and AI agents reach SuggestAPI, which understands the request and keeps context. Your existing search finds and ranks records. Your application takes the next step.
Who starts
People · Apps · AI agents
↓
SuggestAPI
Understands the request · keeps context
↓
Your existing search
Finds and ranks from the index you already run
↓
Your application
Takes the next step
IntentRetrieveCompareRecommendHandoff
One layer for the request
Keep the request through the whole path.
Intent and constraint extraction, search acceleration, and agent discovery sit in front of the engine you already chose, so a new assistant doesn’t mean a new search stack, and a follow-up doesn’t mean starting over.
01 / Understand
Intent & Constraint Extraction
Extract use case, budget, timing, preferences, and constraints from natural language, then send structured filters and ranking context to the search engine you already run. No replatform.
Intent → Retrieve
02 / Accelerate
Search Acceleration
Return relevant results fast: query rewriting, routing, caching, and delivery straight through your existing search stack.
Ask → Find
03 / Agents
Agent Discovery
The same index, structured so AI assistants can search and act. Commerce is one path: compare, recommend, and hand off to checkout. The merchant keeps the cart.
Compare → Handoff
Your search and index stay where they are.
Read the full category story →
Same intent, ready for agents
Built for the agent that needs to finish the job.
Agents need the request kept intact so they can search, compare, and act without changing the index underneath. The same request arrives already interpreted, whether it is a product, a document, or a part number.
{id · title · fields}
- Find it
- Compare it
- Ask it
- Recommend it
- Hand it off Explore the protocols →
Agent path
Intent → structure
For your stack
Keep discovery on the stack you already run.
Keep Algolia, Typesense, Elasticsearch, Meilisearch, or Shopify. SuggestAPI sits in front so you understand the request without replacing the search you already trust. If you don’t have an engine yet, index your own data.
Start with the product data you already own.
Supabase↓Watch the walkthrough
Google Merchant Center
↓
Import shopping feedsorExport shopping feeds
ShopifyCommerce platformAlgoliaSearch engineTypesenseSearch engineElasticsearchSearch engineMeilisearchSearch engineClaude CommerceCommerce agentCloudflare AI SearchAgent search
Adapter notes in Bring Your Own Search.
Built for the agentic web.
Meet people where they already ask.
A request that starts in ChatGPT, Gemini, a copilot, or another agent still needs structured results from the index you already have. SuggestAPI is the discovery layer that makes that handoff possible.
Agents connect over MCP and WebMCP at the SuggestAPI Agent Gateway (agent.suggestapi.com). Search tools cover the index you already run. The commerce path adds four tools: search, recommend, compare, and product lookup. A WebMCP manifest covers browser-oriented agents.
ARDUCPACPMCPA2APAPWebMCPAgent Skills
Requests that start in ChatGPT, Gemini, copilots, or other agents land on the index you already have through SuggestAPI Agent Discovery.
Your index
Discovery
SuggestAPI Agent Discovery
Agent-ready
ChatGPT · Gemini · copilots
apps · custom agents
What leaves your team
Time, infrastructure, integration, and maintenance.
A discovery layer is real work. SuggestAPI takes it off the team, so what remains is search analytics, agent discovery, and ranking you can measure against the business.
Time
In-house3–6 months for a production gateway
With SuggestAPIA proxy in front of the search you already run
Infrastructure
In-houseAgent bursts land on the search cluster
With SuggestAPIEdge cache. On Scale, about $0.60 per 1,000 included requests
Integration
In-houseA wrapper per engine and a project per protocol
With SuggestAPIOne API. Agent Discovery is included on every paid plan
Maintenance
In-houseAn engineer on the gateway, about $150K+/year in opportunity cost
With SuggestAPISchema changes for MCP, UCP, ACP, ARD, and OKF stay on SuggestAPI
Time, infrastructure, integration, and maintenance.
| Work | In-house | With SuggestAPI |
|---|---|---|
| Time | 3–6 months for a production gateway | A proxy in front of the search you already run |
| Infrastructure | Agent bursts land on the search cluster | Edge cache. On Scale, about $0.60 per 1,000 included requests |
| Integration | A wrapper per engine and a project per protocol | One API. Agent Discovery is included on every paid plan |
| Maintenance | An engineer on the gateway, about $150K+/year in opportunity cost | Schema changes for MCP, UCP, ACP, ARD, and OKF stay on SuggestAPI |
Metered usage
A repeat does not have to be another search charge.
When every agent call and every search request lands on a plan that meters usage, the same question is billed again. A SuggestAPI cache hit answers it from the edge.
Another unit
Always on the meter
Each agent call and each search request counts on the plan you already pay, including when they ask the same thing again.
$0.60
Cached
Per 1,000 on Scale. The provider’s meter does not move. The request is a Discovery Request instead.
Where the effort goes
Search analytics
Usage and query events on every plan. See what people and agents asked, and which journeys come back empty.
Agent discovery
The same catalog, published for assistants. MCP, UCP, ACP, ARD, and OKF are included. There is no separate fee per protocol.
Measurable business-aware ranking
Pins, boosts, and schema ranking you control, with the query evidence in front of you. With Convertmax, revenue comes back so ranking can follow conversion and revenue per search, not only clicks.
The 3–6 months is an in-house production gateway. The $0.60 per 1,000 is Scale’s included Discovery Requests (plan price divided by one million). Overage above that allowance is priced separately. The $150K+/year is the opportunity cost of an engineer on gateway maintenance, not a measured saving for every customer. See the cost comparison. Plan limits. Ranking from revenue.
Capture demand your search is losing.
Add a discovery layer without replacing the stack you have.
Connect the search you already run, or index your own data. Understand the request from the first ask through the next step, for people and agents.
{"@context":"https://schema.org","@type":"Organization","name":"SuggestAPI","url":"https://www.suggestapi.com","logo":"https://www.suggestapi.com/suggestapi-logo.png","sameAs":["https://x.com/suggestapi","https://www.linkedin.com/company/suggestapi","https://www.youtube.com/@suggestapi","https://github.com/suggestapi"]}
{"@context":"https://schema.org","@type":"WebSite","name":"SuggestAPI - The Discovery Layer","url":"https://www.suggestapi.com","description":"You have AEO. Do you know how to get the conversion? SuggestAPI is the discovery layer after the citation.","inLanguage":"en","publisher":{"@type":"Organization","name":"SuggestAPI"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://www.suggestapi.com/search/?q={search_term_string}"},"query-input":"required name=search_term_string"}}