vaaya / tools / tavily / search
Tavily search for AI agents
Tavily — AI-native web search tuned for RAG: ranked results with relevance scores, optional LLM answer synthesis. Pass `query`; optional `topic`…
1¢ per call
npx @vaaya/mcp installParameters
| Param | Type | What |
|---|---|---|
query required | string | |
country | string | |
exclude_domains | string[] | |
include_answer | boolean | "basic" | "advanced" | |
include_domains | string[] | |
include_raw_content | boolean | "markdown" | "text" | |
max_results | integer | |
time_range | "day" | "week" | "month" | "year" | "d" | "w" | "m" | "y" | |
topic | "general" | "news" | "finance" |
Call it
In a connected MCP client, pass the service, action, and inputs to use:
{
"service": "tavily",
"action": "search",
"params": {
"query": "<query>"
},
"max_cost_cents": 1
}
Or over HTTP with a Vaaya API key:
curl -X POST https://vaaya.ai/api/run/tavily/search \
-H "Authorization: Bearer $VAAYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"query":"<query>","max_cost_cents":1}'
Service details
Call
tavily/search
Price
1¢. Provider errors are not charged.
Category
Search · routed by vaaya/onesearch
Provider
Settlement
Vaaya calls the provider with its own account and bills you the catalog price.
Credentials
Held server-side by Vaaya; your agent never receives a Tavily key.
More from Tavily
Try this action.
Use the example above in your application, or connect an agent and describe the task. Charges appear in your Vaaya account.
npx @vaaya/mcp install