Skip to main content
Glama

HasData

by com.hasdata
OverviewDiscussionsAdmin

google_scholar_scholar: GET /

hasdata_google_scholar_scholar_getScholarSearchResults

Get Scholar Search Results

Scrapes Google Scholar for a query with author:/source: search helpers, year range (asYlo/asYhi), cited-by and all-versions lookups (cites/cluster), review-article and citation-inclusion filters, language/language-restrict, start/num pagination, and asSdt to scope to case law (asSdt=2006 for all courts, 2003 for Federal courts only, or 4/6/3 plus comma-separated court codes for specific courts) or toggle patents. Returns each organic result with title, link, snippet, publication info (authors with profile links), cited-by count and link, related-articles link, and all-versions count and link; a case-law result links to a scholar_case?case= page and carries a ready-to-call caseHasdataLink. Use for academic research, literature review automation, citation tracking, grounding research agents with scholarly sources, and walking case law straight into google/scholar-case-law.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesSearch query. Supports Google Scholar search helpers such as `author:` and `source:`.
hlNoThe two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`.
lrNoThe 'lr' parameter specifies the language of the websites to return results from. This parameter filters results based on the language of the web content.
numNoMaximum number of results to return per page.
asRrNoSet to 1 to return review articles only, or 0 (default) to return all articles.
safeNoAdult content filtering option.
asSdtNoSearch type/filter. Pick a value below to search case law from a specific court, or use `0,5` for Articles (default) / `7` to include patents. Any comma-separated court-code combination Google Scholar accepts also works here as free text beyond this list. Provide one exact documented value (302 allowed), e.g. `0,5`, `2007`.
asVisNoSet to 1 to exclude citations from the results, or 0 (default) to include them.
asYhiNoReturn results published up to and including this year.
asYloNoReturn results published from this year onward.
citesNoUnique article ID to look up articles that cite it, as returned in a result's `citedBy.citesId`.
startNoResult offset for pagination, where 0 is the first result.
filterNoDefines whether to enable or disable the filters for 'Similar Results' and 'Omitted Results'. Set to 1 (default) to enable these filters, or 0 to disable them.
scisbdNoSort results by date instead of relevance: 1 for abstracts only, 2 for everything. Omit for relevance sorting.
clusterNoUnique article ID to look up all indexed versions of that article, as returned in a result's `versions.clusterId`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / asSdt / description
      Previous value: -"Search type/filter, e.g. `0,5` for the default Articles filter, `4` for case law with court codes, or `0`/`7` for patents."New value: +"Search type/filter. Pick a value below to search case law from a specific court, or use `0,5` for Articles (default) / `7` to include patents. Any comma-separated court-code combination Google Scholar accepts also works here as free text beyond this list. Provide one exact documented value (302 allowed), e.g. `0,5`, `2007`."
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

No annotations, so the description carries the full burden and does well: it explains the search-helper syntax, the cites/cluster ID lookups, the asSdt court-scoping semantics (2006 all courts, 2003 Federal, comma-separated codes), and enumerates returned fields including case-law links. It omits any mention of rate limits, auth, or cost, which matters for a scraping endpoint.

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 purpose and every clause carries functional information, but it is delivered as one sprawling multi-clause sentence that is harder to scan than it needs to be.

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 15-parameter tool with no annotations and no output schema, the description covers the input surface and return fields adequately. It falls short only on operational context (auth, quotas, cost) that an agent would want before invoking a scraper.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real interpretation: asYlo/asYhi as a year range, cites/cluster as cited-by and all-versions lookups, asSdt court-code meanings, and start/num as pagination. This goes beyond restating the 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?

Opens with a specific verb+resource (get Scholar search results / scrape Google Scholar for a query) and enumerates the capabilities (author:/source: helpers, year range, cites/cluster, case-law scoping, pagination). It is clearly distinguishable from the sibling case-law-opinion and citation-format tools.

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 concrete usage contexts (academic research, literature review automation, citation tracking, grounding research agents) and explicitly routes case-law continuation to google/scholar-case-law. It does not, however, state when to prefer the citation-formats sibling or any exclusions.

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

All HasData toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources