Search Google Scholar from Claude via MCP
Let Claude search Google Scholar through MCP. Ask for papers on any topic and get titles, authors, snippets, and citation counts in chat.
Input
Output fields
Sign up on Apify or log in
The Google Scholar | Research Papers, Citations & Author Profiles Actor is ready to run with the inputs already set for "Search Google Scholar from Claude via MCP". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "Search Google Scholar from Claude via MCP" task
The Google Scholar | Research Papers, Citations & Author Profiles Actor will start running based on the input automatically. You can also change all the input fields, like search query, to match your specific use case.
Receive the "Search Google Scholar from Claude via MCP" output
Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as position on page, paper title, paper url, and more.
Integrate into your workflow
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Search Google Scholar from Claude via MCP" task via API.

Integrate "Search Google Scholar from Claude via MCP" into your workflow
Connect "Search Google Scholar from Claude via MCP" with 100+ integrations, or run it via API or MCP.
Webhook
n8n
Make
Zapier
Airbyte
Keboola
IFTTT
Hubspot
GDrive
Gmail
Apify MCP
GitHub
Slack
LangChain
LlamaIndex
Flowise
Pinecone
OpenAI
Mastra
Clay
Each result is one row with position, paper_title, link, snippet and result_id, plus publication_info with the authors and inline_links with cited_by_total. Claude reads the rows back in chat; the dataset stays downloadable as JSON or CSV.
A plain request such as find recent papers on transformer neural networks. Claude fills the q field (the example input is {"q": "transformer neural networks"}) and can add as_ylo, as_yhi or num when you ask for a year range or more results.
The same task runs over the Apify API with no chat client at all: call its run endpoint or use apify-client in Python or Node with a q value, then read the dataset as JSON or CSV. MCP is the conversational door, the API is the scripted one.
Open the task in the Apify Console, choose Actions, then Schedule, and set 0 7 * * * for a run every morning at 7 AM. Claude is not involved in a scheduled run; the saved q is searched on its own and a webhook can post new rows to Slack.
Paste https://mcp.apify.com/?tools=actors,docs,johnvc/google-scholar-api as the server URL in Claude, Cursor or any other MCP client, connect it to your Apify account, and the Google Scholar API shows up as a callable tool.
The Google Scholar API lists no free tier. Searches from Claude bill per query, with multi-page searches counted page by page, plus a small setup fee for each run. The current rate is on the Actor page.
Export Google Scholar Results to CSV is built for a file: you run it in the Console and download the table. Search Google Scholar from Claude via MCP keeps the same q search inside a conversation, so Claude can read the hits and follow one up.