# Websearch

> Search Google via the Serper API. Configure access via /login, then MCP Connections, then Serper (web search). Takes one query and returns titles, URLs, snippets, and knowledge-graph data.

- Skill: `primeintellect-ai/websearch` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add primeintellect-ai/websearch`
- Raw SKILL.md: https://api.skillmd.com/api/skills/primeintellect-ai/websearch/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: primeintellect-ai (https://skillmd.com/u/primeintellect-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/primeintellect-ai/websearch

---


# Web Search

Search the web via the Serper Google Search API.

## Setup

Get a free API key at https://serper.dev, then run `/login` in Prime Agent,
switch to **MCP Connections**, and choose **Serper (web search)** to paste it.
The key is stored in Prime Agent and made available to this skill automatically.

If web search reports a missing key, walk the user through those two steps;
don't ask them to set environment variables.

Optional overrides (environment variables):

- `PRIME_AGENT_WEBSEARCH_TIMEOUT` - HTTP timeout in seconds (default 45).
- `PRIME_AGENT_WEBSEARCH_NUM_RESULTS` - number of organic results to return (default 5).

## Usage

Call the prepared `websearch` import directly in the Python kernel:

```python
print(await websearch("latest Prime Agent release"))
```