Skip to main content
Glama
zoharbabin

Google Researcher MCP

Google Search

google_search
Read-only

Retrieve URLs, titles, and snippets from web search to selectively scrape or filter results yourself.

Instructions

Search the web using Google Custom Search API. Returns a list of URLs with titles and snippets.

When to use:

  • You need URLs to process yourself (e.g., selective scraping)

  • You only need links without full content

  • You want to filter/choose which URLs to scrape

When to use search_and_scrape instead:

  • You need actual page content for research

  • You want content from multiple sources combined

Caching: Results cached for 30 minutes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query string. Use natural language or specific keywords for better results. More specific queries yield better results and more relevant sources.
num_resultsNoNumber of search results to return (1-10). Higher numbers increase processing time and API costs. Use 3-5 for quick research, 8-10 for comprehensive coverage.
time_rangeNoRestrict results to a recent time range. 'day' = last 24 hours, 'week' = last 7 days, 'month' = last 30 days, 'year' = last 365 days. Omit for no time restriction.
site_searchNoLimit results to a specific site (e.g., 'github.com', 'stackoverflow.com'). Useful for domain-specific research.
site_search_filterNoWhether to include or exclude results from site_search. 'include' (default) shows only results from the site, 'exclude' removes results from the site.
exact_termsNoRequired exact phrase that must appear in all results. Useful for finding specific quotes or technical terms.
exclude_termsNoTerms to exclude from search results. Useful for filtering out irrelevant topics. Separate multiple terms with spaces.
languageNoRestrict results to a specific language. Format: 'lang_XX' where XX is ISO 639-1 code (e.g., 'lang_en' for English, 'lang_es' for Spanish, 'lang_fr' for French).
countryNoRestrict results to a specific country. Format: 'countryXX' where XX is ISO 3166-1 alpha-2 code (e.g., 'countryUS' for United States, 'countryGB' for United Kingdom).
safeNoSafe search filtering level. 'off' = no filtering, 'medium' = moderate filtering, 'high' = strict filtering. Defaults to Google's account settings if omitted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlsYesList of URLs returned by the search
queryYesThe search query that was executed
resultCountYesNumber of URLs found
Behavior4/5

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

Annotations already declare readOnlyHint=true (safe read) and openWorldHint=true (variable results). The description adds value by specifying that results are cached for 30 minutes and that only URLs/titles/snippets are returned, not full content. This complements the annotations without contradiction.

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?

The description is concise and well-structured, starting with a clear action statement, followed by bullet-point lists for usage guidance, and a brief caching note. Every sentence serves a purpose, and the formatting is optimized for AI readability.

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?

Given the complexity (10 parameters, sibling tools, output schema present), the description covers purpose, usage guidelines, caching behavior, and explicit alternative tool identification. It leverages the output schema to avoid redundant return value explanations, making it complete for informed tool selection.

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?

The input schema covers all 10 parameters with detailed descriptions (100% coverage). The tool description does not add any additional parameter-specific information beyond what the schema provides. With full schema coverage, a baseline score of 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?

The description clearly states the action ('Search the web using Google Custom Search API') and return format ('list of URLs with titles and snippets'). It distinguishes the tool from its sibling 'search_and_scrape' by specifying when to use each, making the purpose unambiguous.

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?

The description includes explicit 'When to use' and 'When to use search_and_scrape instead' sections, providing clear guidance on when to select this tool over its primary alternative. Caching behavior is also noted, offering comprehensive usage context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zoharbabin/google-researcher-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server