Free web search API for AI agents

curl

curl -s https://relay.agentsearchhq.com/v1/search \
  -H 'content-type: application/json' \
  -d '{"query":"Pocket Network","max_results":5}'

Python

import requests

resp = requests.post(
    "https://relay.agentsearchhq.com/v1/search",
    json={"query": "x402 payment protocol", "max_results": 5},
    timeout=30,
)
if resp.status_code == 429:
    raise SystemExit("Free daily limit reached. Try tomorrow, or switch to paid search.")
resp.raise_for_status()
for hit in resp.json()["results"]:
    print(hit["title"], "-", hit["url"])

As an MCP tool (Claude Desktop, Cursor)

{
  "mcpServers": {
    "agentsearch": {
      "command": "npx",
      "args": ["-y", "@agentsearchhq/agentsearch-mcp"]
    }
  }
}

Request and response fields

Request body: query (required) and max_results (1–5, default 5; values outside the range are clamped). Response: query, result_count, retrieved_at and results[], each with title, url, content, score, published_date and domain. Full schema: search OpenAPI spec.