Skip to main content
Glama
ScrapeBadger MCP Server

ScrapeBadger MCP Server

Official

search_google

Run Google searches and return structured results: organic, ads, knowledge graph, AI Overview, People Also Ask, shopping, forums, videos, and related queries.

Instructions

Search Google and get the structured results page: organic results, ads, knowledge graph, AI Overview, People Also Ask, shopping results, perspectives, discussions and forums, short videos and related searches. Set expand_related_questions to also get the People Also Ask answers.

Input Schema

NameRequiredDescriptionDefault
qYesSearch query (supports Google operators like site:, intitle:)
glNoCountry code (e.g. us, gb, de)us
hlNoLanguage code (e.g. en, fr, de)en
startNoResult offset for paging (0, 10, 20, ...)
locationNoCity-level geo-targeting (e.g. 'New York, USA')
ai_overviewNoAlso fetch an AI Overview that Google loads after the page, and resolve its source links.
expand_related_questionsNoOpen the People Also Ask questions and return their answers: true opens every question the page shows (usually four), a number N opens the first N. Each answered question gets text_blocks and references. Each answered question costs one more search (credits = 20 x (1 + answered)); a question whose answer does not come back is not billed. Adds about a second per question.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does disclose output surface (the enumerated result blocks) and the conditional behavior of expand_related_questions, but the cost model and added latency for that flag live in the schema property, not the description. It says nothing about rate limits, blocking/captcha risk, credit cost of the base call, or pagination limits.

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?

Front-loaded with the verb and resource, then a single efficient sentence covering the optional flag. The long result-type enumeration is justified because there is no output schema, though it could be tightened slightly (e.g., grouping forums/discussions with perspectives).

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

Completeness4/5

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

With no output schema and no annotations, the description does the heavy lifting by naming the result sections a caller will receive and flagging the one non-obvious parameter behavior. It stops short of covering paging semantics, base-call credit cost, or result-count expectations for a complex scraping 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% and each of the 7 parameters is already documented in detail, including the credit formula for expand_related_questions. The description repeats only that the flag returns PAA answers, adding no syntax or format detail beyond the schema, so the baseline 3 applies.

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 goes further to enumerate exactly what the structured result page contains — organic, ads, knowledge graph, AI Overview, PAA, shopping, perspectives, discussions, videos, related searches. An agent immediately understands the tool's output scope, and no sibling (all Twitter tools) overlaps.

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

Usage Guidelines3/5

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

Usage is only implied: the tool is for web searches, and the second sentence notes when to enable expand_related_questions. There is no explicit guidance on when to prefer this over another retrieval tool, no exclusions, and no mention of paging behavior via 'start' or when to set geo/language targets.

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