Skip to main content
Glama
Sign In
ScrapeUnblocker MCP Server

ScrapeUnblocker MCP Server

Official
by ScrapeUnblocker
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Google search results

google_search
Read-only

Run Google searches and return structured JSON results, including real URLs, ads, AI Overview, and related searches, to discover pages before fetching them.

Instructions

Run a Google search through ScrapeUnblocker and return the results page as structured JSON: organic results with their real URLs, favicons, sitelinks and star ratings, ads, the AI Overview, People also ask, related searches with their links, the knowledge panel, top stories, videos, local and shopping results. Use this to discover URLs before fetching them. Set full_urls when you need the exact page URL of every result.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keyword": "<keyword>"
    },
    "name": "google_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordYesThe search query.
full_urlsNoWait until Google gives out every result's real URL. Set it when you need the exact page URL of all results (e.g. to cite or open them); leave it off for quick answers. Google releases a results page's links a few at a time, the last ones up to about 40 seconds after the search: without it a result whose link has not come yet has the site's home page as its `url` (or a Google redirect link), with it the call takes up to about 40 seconds longer. Billed the same.
proxy_countryNoOptional ISO country code to search from, e.g. 'US'.
pages_to_checkNoHow many result pages to collect (default 1).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.10
    • addedInput schema / properties / full_urls
      Added value: +{
+  "description": "Wait until Google gives out every result's real URL. Set it when you need the exact page URL of all results (e.g. to cite or open them); leave it off for quick answers. Google releases a results page's links a few at a time, the last ones up to about 40 seconds after the search: without it a result whose link has not come yet has the site's home page as its `url` (or a Google redirect link), with it the call takes up to about 40 seconds longer. Billed the same.",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv0.12.5
    • removedInput schema / additionalProperties
      Removed value: -false
  3. Addedv0.1.4
  4. Removedv0.1.3
  5. First observedv0.1.2

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare it read-only, open-world and non-destructive; the description adds real behavioral context beyond that — the response shape, the variable latency of link release (up to ~40 seconds), the degraded fallback URL when links are not yet available, and a 'billed the same' cost note. This is exactly the kind of operational detail an agent needs before committing to a slow call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action, with no filler words. The long enumeration of result sections is dense but justified because there is no output schema to document return values elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full burden of describing the return payload and does so thoroughly, plus it discloses latency and cost behavior for the slow path. Nothing material is missing for an agent deciding whether and how to call this.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the `full_urls` schema entry already explains the tradeoff in detail, so the description's closing sentence largely restates it. `pages_to_check` and `proxy_country` are not mentioned in the description at all, leaving it at the baseline for a fully documented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a Google search through ScrapeUnblocker') and immediately enumerates the returned sections (organic results, ads, AI Overview, People also ask, knowledge panel, etc.), so the agent knows exactly what this produces. It also distinguishes itself from the fetch/browse siblings with 'Use this to discover URLs before fetching them.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear usage context ('discover URLs before fetching them') and a conditional rule for the `full_urls` flag, which is the main decision an agent faces here. It does not explicitly route away from vertical siblings like google_images, google_local or google_shopping, so the when-not side is inferred rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools