Find web pages with source links and optional page content. Returns matching web-page titles, descriptions and original URLs, with page content only when requested and available. Use one Toolmu account and a shared prepaid balance across available Tools. Pay per use; no separate supplier subscription is required. The current execution ceiling for this Tool is 0.0072 Toolmu credits per call. This is a maximum, not the settled charge. Before execution, get the current Tool contract and check availability, the latest maximumCredits, your balance and budget. Supplier response credits_used, when present, describes supplier API credits and is not the Toolmu customer charge.
Up to 0.0072 credits / call
The final charge is based on confirmed usage. Unused reserved credits return to your available balance.
Surf
SERP API · Surf
Find web pages with source links and optional page content. Returns matching web-page titles, descriptions and original URLs, with page content only when requested and available. Use one Toolmu account and a shared prepaid balance across available Tools. Pay per use; no separate supplier subscription is required. The current execution ceiling for this Tool is 0.0072 Toolmu credits per call. This is a maximum, not the settled charge. Before execution, get the current Tool contract and check availability, the latest maximumCredits, your balance and budget. Supplier response credits_used, when present, describes supplier API credits and is not the Toolmu customer charge.
You receive
Returns matching web-page titles, descriptions and original URLs, with page content only when requested and available. Search snippets are not full-page evidence. Request include_content when needed and inspect the original source for claims that require verification.
Start with your task
What would you like to find online? Share a topic or question, and I’ll look for relevant pages with source links.
Inputs & outputs
Inspect the current inputs, availability, and maximum charge before starting.
Comma-separated domain filter like coindesk.com or cointelegraph.com. Example: coindesk.com,cointelegraph.com.
Minimum length
1
limitqueryParams.limit
integer
Optional
Results per page. Example: 20. Defaults to 20.
Default
20
Minimum
1
Maximum
100
offsetqueryParams.offset
integer
Optional
Pagination offset. Example: 0. Defaults to 0.
Default
0
Minimum
0
Maximum
9007199254740991
include_contentqueryParams.include_content
boolean
Optional
When false (default), search returns title/url/description only — fast (~2-3s) URL discovery. Set true to also include full markdown content for each result (~5-30KB per result, ~10-15s for limit=5). Use true only when the caller needs page content inline and won't follow up with /web/fetch. Example: False. Defaults to false.
Default
false
View raw JSON
{
"type": "object",
"required": [
"queryParams"
],
"properties": {
"queryParams": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"q"
],
"~standard": {
"vendor": "zod",
"version": 1,
"jsonSchema": {}
},
"properties": {
"q": {
"type": "string",
"maxLength": 100,
"minLength": 2,
"description": "Search query like bitcoin price prediction 2026. Example: bitcoin price prediction 2026."
},
"site": {
"type": "string",
"minLength": 1,
"description": "Comma-separated domain filter like coindesk.com or cointelegraph.com. Example: coindesk.com,cointelegraph.com."
},
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "Results per page. Example: 20. Defaults to 20."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset. Example: 0. Defaults to 0."
},
"include_content": {
"type": "boolean",
"default": false,
"description": "When false (default), search returns title/url/description only — fast (~2-3s) URL discovery. Set true to also include full markdown content for each result (~5-30KB per result, ~10-15s for limit=5). Use true only when the caller needs page content inline and won't follow up with /web/fetch. Example: False. Defaults to false."
}
},
"additionalProperties": false
}
},
"additionalProperties": false
}
Result schema
Output fields have not been documented yet.
Additional notes
Find web pages with source links and optional page content
How to use this Tool
Use the deployed input fields below. Required fields must be supplied; optional filters narrow the result.
queryParams.site (Optional): Comma-separated domain filter like coindesk.com or cointelegraph.com. Example: coindesk.com,cointelegraph.com.
queryParams.limit (Optional): Results per page. Example: 20. Defaults to 20.
queryParams.offset (Optional): Pagination offset. Example: 0. Defaults to 0.
queryParams.include_content (Optional): When false (default), search returns title/url/description only — fast (~2-3s) URL discovery. Set true to also include full markdown content for each result (~5-30KB per result, ~10-15s for limit=5). Use true only when the caller needs page content inline and won't follow up with /web/fetch. Example: False. Defaults to false.
What this Tool returns
Returns matching web-page titles, descriptions and original URLs, with page content only when requested and available.
Response fields and how to read them
The table follows the official response contract, including nested fields and useful response metadata. [] denotes an array item. Required means required within its parent object, not that a conditional parent always exists. A nullable type permits null; an optional field can be absent. Use the documented conditions below to distinguish missing, empty and zero values. Units and reporting windows apply only where explicitly documented.
Field, type and presence
Meaning and conditions
data.[].content
string; Required within parent
Relevant content snippet from the page
data.[].description
string; Required within parent
Short description or meta description of the page
data.[].title
string; Required within parent
Page title from the search result
data.[].url
string; Required within parent
Full URL of the search result page
meta.cached
boolean; Required within parent
Whether this response was served from cache
meta.credits_used
integer; Required within parent; format: int64
Credits deducted for this request
meta.empty_reason
string; Optional within parent
Hint explaining why the data array is empty, when applicable
meta.has_more
boolean; Optional within parent
Whether more items may exist beyond this response. For offset-paged endpoints, continue with a larger offset. For time-series endpoints without offset/cursor controls, true means the requested time range hit an upstream cap; narrow from/to to continue. Omitted when exhaustion cannot be proven.
meta.limit
integer; Required within parent; format: int64
Maximum number of items returned in this response
meta.offset
integer; Required within parent; format: int64
Number of items skipped (pagination offset)
meta.total
integer; Optional within parent; format: int64
Total number of matching items (before pagination). Omitted when total is unknown.
meta.watermark
integer; Optional within parent; format: int64
Warehouse watermark (Unix seconds) this response was computed at, on warehouse-backed endpoints (e.g. Hyperliquid /trades/aggregate) — rows up to this time come from the warehouse, newer rows from the live tail. Omitted elsewhere.
Coverage, units and freshness
Search snippets are not full-page evidence. Request include_content when needed and inspect the original source for claims that require verification.
Inspect any returned observation time, cache status, watermark, pagination and errors using their documented meanings. A successful request alone does not establish complete coverage. Where no freshness or completeness guarantee is documented, treat it as unknown. Saved Examples are historical and viewing them does not refresh data or execute a new call.
Data source and references
Surf supplies this endpoint through its Data API. Response contract and deployed Tool inputs reviewed on 2026-10-03 against official OpenAPI v0.2.102. This is a contract review date, not a data observation time. Coverage depends on the selected endpoint and request.
Use one Toolmu account and a shared prepaid balance across available Tools. Pay per use; no separate supplier subscription is required. The current execution ceiling for this Tool is 0.0072 Toolmu credits per call. This is a maximum, not the settled charge. Before execution, get the current Tool contract and check availability, the latest maximumCredits, your balance and budget. Supplier response credits_used, when present, describes supplier API credits and is not the Toolmu customer charge.
Find a how-to guide
Find pages that explain [how to grow herbs indoors].
Describe a topic or ask a question in plain language, such as “how to grow herbs indoors.” If you only want results from a particular website, name it in your request. You do not need to set a result count or enter website-filter settings. Results normally include page titles, short descriptions and links; ask for page content when you need it, if available.
Returns matching web-page titles, descriptions and original URLs, with page content only when requested and available.
Search snippets are not full-page evidence. Request include_content when needed and inspect the original source for claims that require verification.
Use one Toolmu account and a shared prepaid balance across available Tools. Pay per use; no separate supplier subscription is required. The current execution ceiling for this Tool is 0.0072 Toolmu credits per call. This is a maximum, not the settled charge. Before execution, get the current Tool contract and check availability, the latest maximumCredits, your balance and budget. Supplier response credits_used, when present, describes supplier API credits and is not the Toolmu customer charge.
Ask your agent to Find web pages with source links and optional page content. Provide the required inputs above. If Toolmu is already connected, reuse that connection; otherwise use the setup instructions on this page. Before a paid execution, the agent must read the current Tool contract and check availability, the credit ceiling, balance, budget and your authorization. It should then execute the Tool and explain the returned fields and limitations.
Inspect any returned observation time, cache status, watermark, pagination and errors using their documented meanings. A successful request alone does not establish complete coverage. Where no freshness or completeness guarantee is documented, treat it as unknown. Saved Examples are historical and viewing them does not refresh data or execute a new call.
