Fast Google web search: organic results and related questions, no ads.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Fast Google web search via SerpAPI's google_light engine. Returns organic_results, related_questions and related_searches (lighter and faster than the full Google engine; no ads, inline images or other rich elements). Paginate with start (+10 results per page: 0, 10, 20, …). Localize with location or uule (mutually exclusive), gl/hl for country/language, and lr to restrict result languages.
Search query / keywords (required). Supports standard Google operators (site:, intitle:, quotes, …).
Country code for the search, e.g. 'us', 'uk', 'de'.
Language code, e.g. 'en', 'es', 'fr'.
Restrict results to one or more languages, e.g. 'lang_en' or 'lang_en|lang_fr'.
Exclude auto-corrected (spelling-fix) results: 1 = exclude (use the exact query), 0 = allow (default).
SafeSearch level: 'active' to filter explicit results, 'off' to disable.
Google-encoded location string (uule); advanced alternative to location. Mutually exclusive with location.
Result offset for pagination (0-based): 0 = page 1, 10 = page 2, 20 = page 3, … (+10 per page).
Device to emulate for the search: 'desktop' (default), 'tablet' or 'mobile'.
'Similar Results' and 'Omitted Results' filter: 1 = on (default), 0 = off (show all).
Geographic location to originate the search from, e.g. 'Austin, Texas, United States'. Mutually exclusive with uule.
Force a fresh SerpAPI fetch and bypass this server's result cache. Default false.
Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false.
Google domain to use, e.g. 'google.com', 'google.co.uk', 'google.de'. Default google.com.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http google-search https://mcp.wondel.ai/google-search/mcp
Fast Google web search via SerpAPI's google_light engine. Returns organic_results, related_questions and related_searches (lighter and faster than the full Google engine; no ads, inline images or other rich elements). Paginate with start (+10 results per page: 0, 10, 20, …). Localize with location or uule (mutually exclusive), gl/hl for country/language, and lr to restrict result languages.
| Argument | Type | Description |
|---|---|---|
| q* | string | Search query / keywords (required). Supports standard Google operators (site:, intitle:, quotes, …). |
| gl | string | Country code for the search, e.g. 'us', 'uk', 'de'. |
| hl | string | Language code, e.g. 'en', 'es', 'fr'. |
| lr | string | Restrict results to one or more languages, e.g. 'lang_en' or 'lang_en|lang_fr'. |
| nfpr | integer | Exclude auto-corrected (spelling-fix) results: 1 = exclude (use the exact query), 0 = allow (default). |
| safe | string | SafeSearch level: 'active' to filter explicit results, 'off' to disable. |
| uule | string | Google-encoded location string (uule); advanced alternative to location. Mutually exclusive with location. |
| start | integer | Result offset for pagination (0-based): 0 = page 1, 10 = page 2, 20 = page 3, … (+10 per page). |
| device | string | Device to emulate for the search: 'desktop' (default), 'tablet' or 'mobile'. |
| filter | integer | 'Similar Results' and 'Omitted Results' filter: 1 = on (default), 0 = off (show all). |
| location | string | Geographic location to originate the search from, e.g. 'Austin, Texas, United States'. Mutually exclusive with uule. |
| no_cache | boolean | Force a fresh SerpAPI fetch and bypass this server's result cache. Default false. |
| zero_trace | boolean | Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false. |
| google_domain | string | Google domain to use, e.g. 'google.com', 'google.co.uk', 'google.de'. Default google.com. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Search query / keywords (required). Supports standard Google operators (site:, intitle:, quotes, …)."
},
"gl": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Country code for the search, e.g. 'us', 'uk', 'de'."
},
"hl": {
"type": "string",
"description": "Language code, e.g. 'en', 'es', 'fr'."
},
"lr": {
"type": "string",
"description": "Restrict results to one or more languages, e.g. 'lang_en' or 'lang_en|lang_fr'."
},
"nfpr": {
"type": "integer",
"maximum": 1,
"minimum": 0,
"description": "Exclude auto-corrected (spelling-fix) results: 1 = exclude (use the exact query), 0 = allow (default)."
},
"safe": {
"enum": [
"active",
"off"
],
"type": "string",
"description": "SafeSearch level: 'active' to filter explicit results, 'off' to disable."
},
"uule": {
"type": "string",
"description": "Google-encoded location string (uule); advanced alternative to location. Mutually exclusive with location."
},
"start": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0,
"description": "Result offset for pagination (0-based): 0 = page 1, 10 = page 2, 20 = page 3, … (+10 per page)."
},
"device": {
"enum": [
"desktop",
"tablet",
"mobile"
],
"type": "string",
"description": "Device to emulate for the search: 'desktop' (default), 'tablet' or 'mobile'."
},
"filter": {
"type": "integer",
"maximum": 1,
"minimum": 0,
"description": "'Similar Results' and 'Omitted Results' filter: 1 = on (default), 0 = off (show all)."
},
"location": {
"type": "string",
"description": "Geographic location to originate the search from, e.g. 'Austin, Texas, United States'. Mutually exclusive with uule."
},
"no_cache": {
"type": "boolean",
"description": "Force a fresh SerpAPI fetch and bypass this server's result cache. Default false."
},
"zero_trace": {
"type": "boolean",
"description": "Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false."
},
"google_domain": {
"type": "string",
"description": "Google domain to use, e.g. 'google.com', 'google.co.uk', 'google.de'. Default google.com."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.