web_search searches the web with your configured provider and returns
normalized results, cached by query for 15 minutes (configurable). OpenClaw
also bundles x_search for X (formerly Twitter) posts and web_fetch for
lightweight URL fetching. web_fetch always runs locally; web_search routes
through xAI Responses when Grok is the provider, and x_search always uses
xAI Responses.
web_search is a lightweight HTTP tool, not browser automation. For
JS-heavy sites or logins, use the Web Browser. For
fetching a specific URL, use Web Fetch.Quick start
Choose a provider
Pick a provider and complete any required setup. Some providers are
key-free, others need an API key. See the provider pages below for
details.
Configure
BRAVE_API_KEY) and skip this step.Choosing a provider
Brave Search
Structured results with snippets. Supports
llm-context mode, country/language filters. Free tier available.Codex Hosted Search
AI-synthesized grounded answers through your Codex app-server account.
DuckDuckGo
Key-free provider. No API key needed. Unofficial HTML-based integration.
Exa
Neural + keyword search with content extraction (highlights, text, summaries).
Firecrawl
Structured results. Best paired with
firecrawl_search and firecrawl_scrape for deep extraction.Gemini
AI-synthesized answers with citations via Google Search grounding.
Grok
AI-synthesized answers with citations via xAI web grounding.
Kimi
AI-synthesized answers with citations via Moonshot web search; ungrounded chat fallbacks fail explicitly.
MiniMax Search
Structured results via the MiniMax Token Plan search API.
Ollama Web Search
Search via a signed-in local Ollama host or the hosted Ollama API.
Parallel
Paid Parallel Search API (
PARALLEL_API_KEY); higher rate limits and objective tuning.Parallel Search (Free)
Key-free opt-in. Parallel’s free Search MCP, with LLM-optimized dense excerpts and no API key.
Perplexity
Structured results with content extraction controls and domain filtering.
SearXNG
Self-hosted meta-search. No API key needed. Aggregates Google, Bing, DuckDuckGo, and more.
Tavily
Structured results with search depth, topic filtering, and
tavily_extract for URL extraction.Provider comparison
| Provider | Result style | Filters | API key |
|---|---|---|---|
| Brave | Structured snippets | Country, language, time, llm-context mode | BRAVE_API_KEY |
| Codex Hosted Search | AI-synthesized + source URLs | Domains, context size, user location | None; uses Codex/OpenAI sign-in |
| DuckDuckGo | Structured snippets | — | None (key-free) |
| Exa | Structured + extracted | Neural/keyword mode, date, content extraction | EXA_API_KEY |
| Firecrawl | Structured snippets | Via firecrawl_search tool | FIRECRAWL_API_KEY |
| Gemini | AI-synthesized + citations | — | GEMINI_API_KEY |
| Grok | AI-synthesized + citations | — | xAI OAuth, XAI_API_KEY, or plugins.entries.xai.config.webSearch.apiKey |
| Kimi | AI-synthesized + citations; fails on ungrounded chat fallbacks | — | KIMI_API_KEY / MOONSHOT_API_KEY |
| MiniMax Search | Structured snippets | Region (global / cn) | MINIMAX_CODE_PLAN_KEY / MINIMAX_CODING_API_KEY / MINIMAX_OAUTH_TOKEN |
| Ollama Web Search | Structured snippets | — | None for signed-in local hosts; OLLAMA_API_KEY for direct https://ollama.com search |
| Parallel | Dense excerpts ranked for LLM context | — | PARALLEL_API_KEY (paid) |
| Parallel Search (Free) | Dense excerpts ranked for LLM context | — | None (free Search MCP) |
| Perplexity | Structured snippets | Country, language, time, domains, content limits | PERPLEXITY_API_KEY / OPENROUTER_API_KEY |
| SearXNG | Structured snippets | Categories, language | None (self-hosted) |
| Tavily | Structured snippets | Via tavily_search tool | TAVILY_API_KEY |
Auto-detection
Provider lists in docs and setup flows are alphabetical. Auto-detection uses a separate, fixed precedence order and only picks a provider that needs a credential (requiresCredential !== false) when it finds one configured. If
no provider is set, OpenClaw checks providers in this order and uses the
first one that is ready:
API-backed providers first:
- Brave —
BRAVE_API_KEYorplugins.entries.brave.config.webSearch.apiKey(order 10) - MiniMax Search —
MINIMAX_CODE_PLAN_KEY/MINIMAX_CODING_API_KEY/MINIMAX_OAUTH_TOKEN/MINIMAX_API_KEYorplugins.entries.minimax.config.webSearch.apiKey(order 15) - Gemini —
plugins.entries.google.config.webSearch.apiKey,GEMINI_API_KEY, ormodels.providers.google.apiKey(order 20) - Grok — xAI OAuth,
XAI_API_KEY, orplugins.entries.xai.config.webSearch.apiKey(order 30) - Kimi —
KIMI_API_KEY/MOONSHOT_API_KEYorplugins.entries.moonshot.config.webSearch.apiKey(order 40) - Perplexity —
PERPLEXITY_API_KEY/OPENROUTER_API_KEYorplugins.entries.perplexity.config.webSearch.apiKey(order 50) - Firecrawl —
FIRECRAWL_API_KEYorplugins.entries.firecrawl.config.webSearch.apiKey(order 60) - Exa —
EXA_API_KEYorplugins.entries.exa.config.webSearch.apiKey; optionalplugins.entries.exa.config.webSearch.baseUrloverrides the Exa endpoint (order 65) - Tavily —
TAVILY_API_KEYorplugins.entries.tavily.config.webSearch.apiKey(order 70) - Parallel — paid Parallel Search API via
PARALLEL_API_KEYorplugins.entries.parallel.config.webSearch.apiKey; optionalplugins.entries.parallel.config.webSearch.baseUrloverrides the endpoint (order 75)
- SearXNG —
SEARXNG_BASE_URLorplugins.entries.searxng.config.webSearch.baseUrl(order 200)
tools.web.search.provider or through
openclaw configure --section web. OpenClaw does not send managed
web_search queries to a key-free provider just because no API-backed
provider is configured.
OpenAI Responses models are an exception: while tools.web.search.provider
is unset, they use OpenAI’s native web search instead of the managed
providers above (see below). Set tools.web.search.provider to
parallel-free (or another provider) to route them through the managed path
instead.
All provider key fields support SecretRef objects. Plugin-scoped SecretRefs
under
plugins.entries.<plugin>.config.webSearch.apiKey are resolved for the
installed API-backed web search providers, including Brave, Exa, Firecrawl,
Gemini, Grok, Kimi, MiniMax, Parallel, Perplexity, and Tavily,
whether the provider is picked explicitly via tools.web.search.provider or
selected through auto-detect. In auto-detect mode, OpenClaw resolves only the
selected provider key — non-selected SecretRefs stay inactive, so you can
keep multiple providers configured without paying resolution cost for the
ones you are not using.Native OpenAI web search
Direct OpenAI Responses models (api: "openai-responses", provider openai,
no base URL or an official OpenAI API base URL) use OpenAI’s hosted
web_search tool automatically when OpenClaw web search is enabled and no
managed provider is pinned. This is provider-owned behavior in the bundled
OpenAI plugin and does not apply to OpenAI-compatible proxy base URLs or Azure
routes. Set tools.web.search.provider to another provider such as brave to
keep the managed web_search tool for OpenAI models, or set
tools.web.search.enabled: false to disable both managed search and native
OpenAI search.
Native Codex web search
The Codex app-server runtime uses Codex’s hostedweb_search tool automatically
when web search is enabled and no managed provider is selected. Native hosted
search and OpenClaw’s managed web_search dynamic tool are mutually exclusive,
so managed search cannot bypass native domain restrictions. OpenClaw uses the
managed tool when hosted search is unavailable, explicitly disabled, or
replaced by a selected managed provider. OpenClaw keeps Codex’s standalone
web.run extension disabled (features.standalone_web_search: false)
because production app-server traffic rejects its user-defined web
namespace.
- Configure native search under
tools.web.search.openaiCodex - Set
tools.web.search.provider: "codex"to provision Codex Hosted Search as the managedweb_searchprovider for any parent model. Each call runs a bounded ephemeral Codex app-server turn and fails if Codex does not emit a hostedwebSearchitem. mode: "cached"is the default preference, but Codex resolves it to live external access for unrestricted app-server turns; set"live"to request live access explicitly- Set
tools.web.search.providerto a managed provider such asbraveto use OpenClaw’s managedweb_searchinstead - Set
tools.web.search.openaiCodex.enabled: falseto opt out of Codex-hosted search; other managed providers remain available - Restricting the Codex native tool surface also keeps managed
web_searchavailable - When
allowedDomainsis set, automatic managed fallback fails closed if hosted search is unavailable so the native allowlist cannot be bypassed - Tool-disabled LLM-only runs disable both native and managed search
tools.web.search.enabled: falsedisables both managed and native search
web_search tool. That separate path remains opt-in through
tools.web.search.openaiCodex.enabled: true and only applies to eligible
openai/* models using api: "openai-chatgpt-responses".
web_search fallback through OpenClaw’s dynamic tool namespace.
Use an explicit managed provider when you need OpenClaw’s provider-specific
network controls instead of Codex-hosted search.
Selecting provider: "codex" enables the bundled codex plugin and uses the
same tools.web.search.openaiCodex restrictions shown above. Authenticate the
Codex app-server first with openclaw models auth login --provider openai.
The parent agent can use any model or runtime; only the bounded search worker
runs through Codex.
Network safety
Managed HTTPweb_search provider calls use OpenClaw’s guarded fetch path,
scoped to the current provider’s own hostname. For that hostname only,
OpenClaw allows Surge, Clash, and sing-box fake-IP DNS answers in
198.18.0.0/15 and fc00::/7. Other private, loopback, link-local, and
metadata destinations remain blocked. Codex Hosted Search is the exception:
its bounded worker delegates network access to Codex app-server’s hosted
web_search tool.
This automatic allowance does not apply to arbitrary web_fetch URLs. For
web_fetch, enable tools.web.fetch.ssrfPolicy.allowRfc2544BenchmarkRange and
tools.web.fetch.ssrfPolicy.allowIpv6UniqueLocalRange explicitly only when your
trusted proxy owns those synthetic ranges.
Config
plugins.entries.<plugin>.config.webSearch.*. Gemini can also reuse
models.providers.google.apiKey and models.providers.google.baseUrl as lower-priority
fallbacks after its dedicated web-search config and GEMINI_API_KEY. See the
provider pages for examples.
Grok can also reuse an xAI OAuth auth profile from openclaw models auth login --provider xai --method oauth; API-key config remains the fallback.
tools.web.search.provider is validated against the web-search provider ids
declared by bundled and installed plugin manifests. A typo such as "brvae"
fails config validation instead of silently falling back to auto-detection. If a
configured provider only has stale plugin evidence, such as a leftover
plugins.entries.<plugin> block after uninstalling a third-party plugin,
OpenClaw keeps startup resilient and reports a warning so you can reinstall the
plugin or run openclaw doctor --fix to clean up the stale config.
web_fetch fallback provider selection is separate:
- choose it with
tools.web.fetch.provider - or omit that field and let OpenClaw auto-detect the first ready web-fetch provider from configured credentials
- non-sandboxed
web_fetchcan use installed plugin providers that declarecontracts.webFetchProviders; sandboxed fetches allow bundled providers and verified official plugin installs, but exclude third-party external plugins - the official Firecrawl plugin is the only bundled
webFetchProviderscontributor today, configured underplugins.entries.firecrawl.config.webFetch.*
openclaw onboard or
openclaw configure --section web, OpenClaw can also ask for:
- the Moonshot API region (
https://api.moonshot.ai/v1orhttps://api.moonshot.cn/v1) - the default Kimi web-search model (defaults to
kimi-k2.6)
x_search, configure plugins.entries.xai.config.xSearch.*. It uses the
same xAI auth profile as chat, or the XAI_API_KEY / plugin web-search
credential used by Grok web search.
Legacy tools.web.x_search.* config is auto-migrated by openclaw doctor --fix.
When you choose Grok during openclaw onboard or openclaw configure --section web,
OpenClaw also offers optional x_search setup with the same credential right
after Grok setup completes. This is a separate follow-up step inside the Grok
path, not a separate top-level web-search provider choice. If you pick another
provider, OpenClaw does not show the x_search prompt.
Storing API keys
- Config file
- Environment variable
Run
openclaw configure --section web or set the key directly:Tool parameters
| Parameter | Description |
|---|---|
query | Search query (required) |
count | Results to return (1-10, default: 5) |
country | 2-letter ISO country code (e.g. “US”, “DE”) |
language | ISO 639-1 language code (e.g. “en”, “de”) |
search_lang | Search-language code (Brave only) |
freshness | Time filter: day, week, month, or year |
date_after | Results after this date (YYYY-MM-DD) |
date_before | Results before this date (YYYY-MM-DD) |
ui_lang | UI language code (Brave only) |
domain_filter | Domain allowlist/denylist array (Perplexity only) |
max_tokens | Total content token budget, native Perplexity Search API only |
max_tokens_per_page | Per-page extraction token limit, native Perplexity Search API only |
x_search
x_search queries X (formerly Twitter) posts using xAI and returns
AI-synthesized answers with citations. It accepts natural-language queries and
optional structured filters. OpenClaw constructs the built-in xAI x_search
tool per request rather than keeping it permanently registered, so it is only
active for the turn that actually calls it.
xAI documents
x_search as supporting keyword search, semantic search, user
search, and thread fetch. For per-post engagement stats such as reposts,
replies, bookmarks, or views, prefer a targeted lookup for the exact post URL
or status ID. Broad keyword searches may find the right post but return less
complete per-post metadata. A good pattern is: locate the post first, then
run a second x_search query focused on that exact post.x_search config
x_search posts to <baseUrl>/responses when
plugins.entries.xai.config.xSearch.baseUrl is set. If that field is omitted,
it falls back to plugins.entries.xai.config.webSearch.baseUrl, then the
legacy tools.web.search.grok.baseUrl, and finally the public xAI endpoint
(https://api.x.ai/v1).
x_search parameters
| Parameter | Description |
|---|---|
query | Search query (required) |
allowed_x_handles | Restrict results to specific X handles |
excluded_x_handles | Exclude specific X handles |
from_date | Only include posts on or after this date (YYYY-MM-DD) |
to_date | Only include posts on or before this date (YYYY-MM-DD) |
enable_image_understanding | Let xAI inspect images attached to matching posts |
enable_video_understanding | Let xAI inspect videos attached to matching posts |
x_search example
Examples
Tool profiles
If you use tool profiles or allowlists, addweb_search, x_search, or group:web:
Related
- Web Fetch — fetch a URL and extract readable content
- Web Browser — full browser automation for JS-heavy sites
- Grok Search — Grok as the
web_searchprovider - Ollama Web Search — key-free web search through your Ollama host