Skip to main content
Glama

Scholar MCP

Local MCP server that searches Google Scholar. Scrapes results with requests + BeautifulSoup -- no API keys, no paid services.

Tools

  • search_papers_by_topic -- search by keywords, optional year range, paginated

  • get_author_papers -- find papers by author name, paginated

Related MCP server: semantic-scholar-mcp

Install

Clone and install:

git clone https://github.com/ProPriyam/Scholar-MCP.git
cd Scholar-MCP
pip install -e .

Or run directly without cloning (needs uv):

uvx --from git+https://github.com/ProPriyam/Scholar-MCP scholar-mcp

Client setup

All configs use python -m scholar_mcp.server to start the server. This avoids PATH issues that pip install can cause on Windows.

VS Code

Add to .vscode/mcp.json:

{
	"servers": {
		"scholarMcp": {
			"type": "stdio",
			"command": "python",
			"args": ["-m", "scholar_mcp.server"],
			"env": {
				"PYTHONUNBUFFERED": "1"
			}
		}
	}
}

OpenCode

Add to opencode.json in your project root:

{
	"$schema": "https://opencode.ai/config.json",
	"mcp": {
		"scholar_mcp": {
			"type": "local",
			"command": ["python", "-m", "scholar_mcp.server"],
			"enabled": true,
			"environment": {
				"PYTHONUNBUFFERED": "1"
			}
		}
	}
}

Claude Code

claude mcp add --transport stdio --scope project scholar-mcp -- python -m scholar_mcp.server

Configuration

All optional. Set as environment variables.

Variable

Default

Description

SCHOLAR_USER_AGENT

Chrome-like UA

User-Agent header for requests

SCHOLAR_TIMEOUT

20

HTTP timeout in seconds

SCHOLAR_MIN_DELAY

1.2

Minimum delay between requests (seconds)

SCHOLAR_MAX_RETRIES

2

Retry attempts on failure

SCHOLAR_RETRY_BACKOFF

1.5

Backoff multiplier between retries

SCHOLAR_PROXY_URL

none

HTTP/HTTPS proxy URL

SCHOLAR_MAX_PAGE_SIZE

20

Max results per request

Notes

  • This scrapes Google Scholar HTML. It can break if Google changes their markup or blocks requests.

Available Tools

2 tools
get_author_papersB

Get papers filtered by author name from Google Scholar search.

Inputs: author (required), page_size, cursor. Returns: object

search_papers_by_topicC

Search Google Scholar papers by topic keywords.

Inputs: query (required), page_size, cursor, year_min, +1 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one filters papers by author name, while the other searches by topic keywords. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the query.

    Naming Consistency4/5

    Both tools follow a verb_noun pattern (get_author_papers, search_papers_by_topic), which is consistent and readable. The minor deviation is in the prepositional phrase 'by_topic' vs. no preposition in the first name, but this does not hinder clarity.

    Tool Count2/5

    With only 2 tools, the server feels thin and under-scoped for a Google Scholar integration. Key operations like retrieving paper details, citations, or author profiles are missing, limiting the server's utility for comprehensive scholarly research.

    Completeness2/5

    The toolset is severely incomplete for a Google Scholar domain. It lacks basic CRUD operations such as getting paper metadata, author information, or citation counts, and there are no update or delete capabilities, leaving significant gaps for agent workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that enables academic research by searching Google Scholar, fetching paper content, and converting web pages to clean Markdown.
      1
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      An MCP server that provides access to Semantic Scholar's academic paper database, enabling paper search, detailed retrieval, author info, and citation export.
      4
      10
      -
    • A
      license
      A
      quality
      B
      maintenance
      An MCP server for searching Google Scholar, enabling paper search, author lookup, citation tracking, and BibTeX export for AI assistants and automation workflows.
      5
      2
      MIT