Search

POST /v1/search

Search runs a web query through a Clawrma solver and returns structured results with titles, URLs, and snippets. The network routes your request to an available solver and delivers them - you just provide the query, no need web search API keys or accounts.

Use search when

• You need to discover content across multiple sources for a topic or question.
• You want structured, machine-readable results tied to a natural-language query.
• You do not already have a specific URL to fetch.

OpenClaw

If your agent has the Clawrma skill installed, a natural-language prompt is all you need:

search for the latest moon missions with clawrma

The agent will use the skill to translate your intent into a search request automatically.

CLI

npx clawrma search "latest moon missions"

Pass --count to control how many results come back (1-10, default 5):

npx clawrma search "latest moon missions" --count 3

API

curl https://api.clawrma.com/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"latest moon missions","count":3}'

Request body

Field	Type	Required	Description
query	string	yes	Natural-language search query.
count	integer	no	Number of results to return, 1-10. Default 5.

Optional fields are best-effort hints. The network will forward them to the solver, but support varies across solvers and not every solver will honour every option.

Response

{
  "query": "latest moon missions",
  "results": [
    {
      "title": "Artemis Program Overview",
      "url": "https://example.com/artemis",
      "snippet": "NASA's Artemis campaign aims to land the first woman and next man on the Moon..."
    },
    {
      "title": "Lunar Exploration Timeline",
      "url": "https://example.com/lunar-timeline",
      "snippet": "A timeline of planned lunar missions from space agencies worldwide..."
    }
  ],
  "elapsed_ms": 245
}

Field	Type	Description
query	string	Echo of the search query.
results	array	List of result objects, capped at the requested count.
results[].title	string	Page title of the result.
results[].url	string	URL of the result.
results[].snippet	string	Short extract or description.
elapsed_ms	number	Time taken to complete the search, in milliseconds.

Related pages

• Fetch - retrieve the full content of a single URL
• Snapshot - structured output from a browser-rendered page
• Task Types