Skip to main content
Glama

Litescrape

by com.litescrape
OverviewDiscussionsAdmin

Google Search

google_search
Read-only

Fetch a first-party Google Search results page as JSON: organic_results plus whichever modules Google served (knowledge_graph, answer_box, ai_overview, ads, related_questions, related_searches, local_results, top_stories, inline_videos and more). Supports localization, verticals (news, videos, local, shopping, patents), date filters and site restriction. Free without an API key: 25 calls per network per day.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch query; required unless ludocid or kgmid is supplied
crNoCountry restrict such as countryUS|countryCA
glNoTwo-letter country for localization, e.g. "us"
hlNoLanguage code such as "en" or "en-GB"; default en
lrNoLanguage restrict such as lang_en|lang_fr
latNoLatitude; supply together with lon
lonNoLongitude; supply together with lat
numNoRequested result count, 1-100; Google may return fewer
tbmNoVertical: lcl local, vid videos, nws news, shop shopping, pts patents
tbsNoGoogle search-filter string, e.g. qdr:w for the past week
nfprNo1 disables spelling auto-correction
safeNoSafeSearch
uuleNoPre-encoded Google location token; conflicts with location
kgmidNoKnowledge Graph machine ID such as /m/0k8z
startNoResult offset for pagination
as_qdrNoDate range: d, w, m or y with an optional count, e.g. d7 for the past week
deviceNoLayout to request; default desktop
filterNo0 disables duplicate-content filtering
radiusNoRadius in meters around the location or coordinates
ludocidNoGoogle CID of a local entity, for a targeted lookup
locationNoNamed search origin such as "Austin, Texas"; conflicts with uule and lat/lon
fast_modeNotrue returns only organic_results (faster and smaller); skips AI Overview, Knowledge Graph, ads and every other module
as_sitesearchNoRestrict results to this hostname
google_domainNoGoogle domain such as google.co.uk; default google.com
result_groupsNoReturn only these top-level result groups, e.g. ["organic_results", "knowledge_graph"]; omit for the complete response. search_metadata is always kept

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true; the description adds useful transparent details: results include whatever modules Google happens to serve, no API key is needed, and there is a 25-call-per-network-per-day limit. No contradiction with annotations.

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?

Two dense sentences with no filler. The most important information, what is returned and which service is queried, comes first, and the capability summary in the second sentence earns its place.

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?

For a complex tool with 25 parameters and no output schema, the description covers the essential choices: result content, supported modules, localization/vertical/filter options, and quota constraints. It does not provide an example or elaborate on every behavior, but the rich schema plus these capabilities make it sufficiently complete for a tool-selection and invocation decision.

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%, so the schema already documents all 25 parameters. The description adds high-level groupings like 'localization, verticals, date filters' but does not explain any parameter beyond what the schema provides, so baseline 3 is appropriate.

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 ('Fetch') and resource ('Google Search results page as JSON'), and enumerates what is returned. It clearly distinguishes this first-party Google search tool from sibling tools like bing_search, duckduckgo_search, and google_maps.

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?

The description gives strong context: it is for first-party Google results and lists supported capabilities like localization, verticals, and date filters. It does not explicitly name alternatives or say when not to use it, but the use case is clear enough for an agent to select it appropriately.

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

All Litescrape toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources