google-scholar-search-mcp

Getting Started

  • Installation
    • Prerequisites
    • Recommended: uv and one-command setup
    • Install from PyPI
    • Install with Poetry (recommended)
    • Build from Source
    • MCP Client Setup
      • Claude Desktop
      • Other MCP Clients
    • Building the Docs
  • Quickstart
    • Search by Topic
    • Get Full Paper Details
    • Find Citing Papers
    • Batch Literature Review
    • Export BibTeX

Tool Reference

  • Tool Reference
    • search_papers
      • Parameters
      • Return Value
      • Paging
      • Examples
    • get_paper_details
      • Parameters
      • Return Value
      • Examples
    • get_citations
      • Parameters
      • Return Value
      • Examples
    • bulk_search
      • Parameters
      • Return Value
      • Examples
    • get_bibtex
      • Parameters
      • Return Value
      • Examples

Configuration

  • Configuration
    • Defaults
    • Environment Variables
    • Browser Cookies (experimental)
    • Proxy Modes
    • Agent Skill
    • Passing Config via Claude Desktop
    • Extending Config

API Reference

  • API Reference
    • server
      • main()
    • models
      • PaperResult
      • PaperDetails
      • SearchResponse
      • BulkSearchResponse
      • CitationResponse
    • config
    • scholar
      • require_identifier()
      • ScholarClient
    • rate_limiter
      • RateLimiter
    • throttle
      • RequestThrottle
    • cache
      • TTLCache
      • normalize()
    • errors
      • ScholarError
      • ScholarNotFoundError
      • ScholarRateLimitError
      • ScholarBlockedError
      • ScholarInvalidArgumentError
    • block_detector
      • classify()
      • BlockDetector
    • session_identity
      • parse_cookies()
      • default_cookie_file()
      • split_identity()
      • write_identity_file()
      • login_cookie_names()
      • set_identity()
      • current_cookie_names()
      • apply_identity()
    • cli
      • setup()
      • main()
      • clients
      • targets
      • skill
google-scholar-search-mcp
  • Tool Reference
  • bulk_search
  • Edit on GitHub

bulk_search

Search Google Scholar for multiple queries sequentially with automatic rate limiting.

Use this tool for batch literature reviews when you need results for several topics at once. Each query runs one at a time with randomised delays between them to avoid triggering Google Scholar’s bot detection. Partial failures are captured per-query so a single bad result does not abort the whole batch.

Parameters

Parameter

Type

Default

Description

queries

list[str]

(required)

List of search queries. Maximum 10 queries per call.

max_results_per_query

int

5

Results to return for each query. Clamped to 1–10.

year_from

int

None

Filter to papers published in or after this year (applied to all queries).

year_to

int

None

Filter to papers published in or before this year (applied to all queries).

Return Value

Returns a BulkSearchResponse containing:

  • results — list of SearchResponse, one per query

  • total_queries — number of queries submitted

  • completed_queries — number of queries that succeeded

  • errors — list of error strings for any failed queries

Examples

Multi-topic literature sweep:

{
  "queries": [
    "diffusion models image generation",
    "contrastive self-supervised learning",
    "neural radiance fields NeRF"
  ],
  "max_results_per_query": 5
}

Year-filtered batch search:

{
  "queries": [
    "large language model alignment",
    "reinforcement learning from human feedback"
  ],
  "max_results_per_query": 8,
  "year_from": 2022
}

Warning

Even with rate limiting, large batches (10 queries) can take several minutes. Prefer smaller batches or lower max_results_per_query when low latency matters.

Previous Next

© Copyright 2026, Lucas Waetzig.

Built with Sphinx using a theme provided by Read the Docs.