Skip to main content
The Go SDK and docs are currently in beta. Report issues on GitHub.
Configuration for the openrouter:web_fetch server tool

​
Fields

FieldTypeRequiredDescriptionExample
AllowedDomains[]string:heavy_minus_sign:Only fetch from these domains.
BlockedDomains[]string:heavy_minus_sign:Never fetch from these domains.
Engine*components.WebFetchEngineEnum:heavy_minus_sign:Which fetch engine to use. “auto” (default) uses native if the provider supports it, otherwise Exa. “native” forces the provider’s built-in fetch. “exa” uses Exa Contents API. “openrouter” uses direct HTTP fetch. “firecrawl” uses Firecrawl scrape (requires BYOK). “parallel” uses the Parallel extract API.auto
MaxContentTokens*int64:heavy_minus_sign:Maximum content length in approximate tokens. Content exceeding this limit is truncated.100000
MaxUses*int64:heavy_minus_sign:Maximum number of web fetches per request. Once exceeded, the tool returns an error.10