OpenClaw includes two powerful tools for internet access:

1. web_search: Find information using search engines (Brave or Perplexity).
2. web_fetch: Retrieve and read the content of specific web pages (HTML to Markdown).

OpenClaw supports two providers for web search:

You can configure the search provider in ~/.openclaw/openclaw.json.

{
  tools: {
    web: {
      search: {
        provider: "brave",
        apiKey: "BSA-..." // Optional if env var set
      }
    }
  }
}

{
  tools: {
    web: {
      search: {
        provider: "perplexity",
        perplexity: {
          apiKey: "sk-or-...", // Optional if env var set
          model: "perplexity/sonar-pro"
        }
      }
    }
  }
}

The web_fetch tool downloads a webpage and converts it to readable text (Markdown) for the agent.

• Auto-Fallback: If a direct fetch fails (e.g., due to anti-bot protection), it can automatically try Firecrawl if configured.
• Privacy: Fetches are done from the Gateway server IP.

The agent decides when to use these tools. You might see logs like:

[agent] invoking tool: web_search({ query: "latest SpaceX launch" })
[agent] invoking tool: web_fetch({ url: "https://www.spacex.com/launches/" })

{
  tools: {
    web: {
      search: {
        enabled: true,
        maxResults: 5,
        cacheTtlMinutes: 15 // Cache results to save API credits
      },
      fetch: {
        timeoutSeconds: 30,
        userAgent: "OpenClaw/1.0" // Custom User-Agent
      }
    }
  }
}

freshness: “pw” });

## web_fetch

Fetch a URL and extract readable content.

### Requirements

- `tools.web.fetch.enabled` must not be `false` (default: enabled)
- Optional Firecrawl fallback: set `tools.web.fetch.firecrawl.apiKey` or `FIRECRAWL_API_KEY`.

### Config

```json5
{
  tools: {
    web: {
      fetch: {
        enabled: true,
        maxChars: 50000,
        timeoutSeconds: 30,
        cacheTtlMinutes: 15,
        maxRedirects: 3,
        userAgent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 14_7_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
        readability: true,
        firecrawl: {
          enabled: true,
          apiKey: "FIRECRAWL_API_KEY_HERE", // optional if FIRECRAWL_API_KEY is set
          baseUrl: "https://api.firecrawl.dev",
          onlyMainContent: true,
          maxAgeMs: 86400000, // ms (1 day)
          timeoutSeconds: 60
        }
      }
    }
  }
}

• url (required, http/https only)
• extractMode (markdown | text)
• maxChars (truncate long pages)

Notes:

• web_fetch uses Readability (main-content extraction) first, then Firecrawl (if configured). If both fail, the tool returns an error.
• Firecrawl requests use bot-circumvention mode and cache results by default.
• web_fetch sends a Chrome-like User-Agent and Accept-Language by default; override userAgent if needed.
• web_fetch blocks private/internal hostnames and re-checks redirects (limit with maxRedirects).
• web_fetch is best-effort extraction; some sites will need the browser tool.
• See Firecrawl for key setup and service details.
• Responses are cached (default 15 minutes) to reduce repeated fetches.
• If you use tool profiles/allowlists, add web_search/web_fetch or group:web.
• If the Brave key is missing, web_search returns a short setup hint with a docs link.