Skip to main content
Glama
Sign In
WebScraping-AI MCP Server

WebScraping-AI MCP Server

Official
by webscraping-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Search Google

webscraping_ai_serp
Read-only

Search Google and get parsed JSON results—titles, links, snippets, related searches, and pagination—from a fixed location so repeat searches and later pages stay consistent.

Instructions

Search Google and get parsed results as JSON: organic_results (position, title, link, domain, displayed_link, snippet, date), related_searches, search_information (including spelling corrections) and pagination. 10 results per page; position restarts at 1 on every page. Every search runs from one fixed location (location, lat and lon, or uule; otherwise the capital of the gl country), so repeats and later pages stay consistent. pages fetches up to 5 consecutive pages in one call as one de-duplicated list. Priced per results page returned (see https://webscraping.ai/docs#serp); failed searches are not charged. Use it to find pages, then read them with webscraping_ai_text or the other tools.

Input Schema

NameRequiredDescriptionDefault
qYesSearch query.
glNoTwo-letter country code for the search, e.g. us, gb, de. Defaults to the country of location, lat/lon or uule, otherwise us.
hlNoTwo-letter language code for the results, e.g. en, de, fr (en by default).
latNoLatitude of the search origin in decimal degrees, from -90 to 90. Requires lon; cannot be combined with location or uule.
lonNoLongitude of the search origin in decimal degrees, from -180 to 180. Requires lat; cannot be combined with location or uule.
pageNoResults page number, 10 results per page (1 by default).
uuleNoGoogle-encoded location (w+CAIQICI… or a+…). Cannot be combined with location, lat or lon.
pagesNoNumber of consecutive results pages to fetch in one call, starting at page, from 1 to 5 (1 by default). Duplicates across pages are removed, position counts through the combined list and each result gets a page field.
engineNoSearch engine to query (google by default).
radiusNoRadius in meters around location or lat/lon, from 1 to 1000.
locationNoWhere the search runs from: a location name such as Austin,Texas,United States or Austin, TX, or an id from webscraping_ai_serp_locations. Large cities also match local names, e.g. Москва. An unknown name returns an error and is not charged. Cannot be combined with uule, lat or lon.
disable_content_sandboxingNoReturn the raw result without the external-content security boundaries that guard against prompt injection (false by default).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv1.4.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / disable_content_sandboxing
      Added value: +{
+  "description": "Return the raw result without the external-content security boundaries that guard against prompt injection (false by default).",
+  "type": "boolean"
+}
    • changedInput schema / properties / gl / description
      Previous value: -"Two-letter country code for the search, e.g. us, gb, de (us by default)."New value: +"Two-letter country code for the search, e.g. us, gb, de. Defaults to the country of location, lat/lon or uule, otherwise us."
    • addedInput schema / properties / lat
      Added value: +{
+  "description": "Latitude of the search origin in decimal degrees, from -90 to 90. Requires lon; cannot be combined with location or uule.",
+  "type": "number"
+}
    • addedInput schema / properties / location
      Added value: +{
+  "description": "Where the search runs from: a location name such as Austin,Texas,United States or Austin, TX, or an id from webscraping_ai_serp_locations. Large cities also match local names, e.g. Москва. An unknown name returns an error and is not charged. Cannot be combined with uule, lat or lon.",
+  "type": "string"
+}
    • addedInput schema / properties / lon
      Added value: +{
+  "description": "Longitude of the search origin in decimal degrees, from -180 to 180. Requires lat; cannot be combined with location or uule.",
+  "type": "number"
+}
    • addedInput schema / properties / page / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / pages
      Added value: +{
+  "description": "Number of consecutive results pages to fetch in one call, starting at page, from 1 to 5 (1 by default). Duplicates across pages are removed, position counts through the combined list and each result gets a page field.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / radius
      Added value: +{
+  "description": "Radius in meters around location or lat/lon, from 1 to 1000.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / uule
      Added value: +{
+  "description": "Google-encoded location (w+CAIQICI… or a+…). Cannot be combined with location, lat or lon.",
+  "type": "string"
+}
  2. Addedv1.2.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already establish it as a read-only, open-world, non-destructive operation. The description adds substantive behavior beyond annotations: fixed-location consistency across repeats and pages, de-duplication in multi-page fetches, pricing per results page, and no charge for failed searches.

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

Conciseness5/5

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

Front-loads the tool's purpose and return structure, then covers pagination, location consistency, pricing, and workflow guidance. The density is justified by the tool's complexity and no sentence is clearly wasteful.

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?

No output schema exists, but the description explains the returned JSON sections well enough for an agent to understand results. It also covers key operational constraints such as page limits, location consistency, and charging for a 12-parameter tool.

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 description coverage is 100%, so every parameter is already documented in detail. The description reinforces location consistency, page position behavior, and pricing, but mostly repeats or summarizes what the schema already says rather than adding new parameter-level meaning.

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: search Google and get parsed JSON results. It enumerates the returned sections (organic_results, related_searches, search_information, pagination), which makes it clearly distinguishable from sibling extraction tools.

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

Usage Guidelines5/5

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

Explains its role in the workflow: use it to find pages, then read them with webscraping_ai_text or the other tools. It also notes when multi-page fetching is appropriate via pages and describes charging behavior for failed searches.

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