Finds papers by title, topic, or text snippet, traces citations and references, and profiles authors with their publication metrics.
20actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro searches the Semantic Scholar database for academic papers ranked by relevance to a query. The customer finds peer-reviewed sources without wading through irrelevant results.
Ayro searches Semantic Scholar for academic authors and their profiles. The team identifies experts and cites their publications to support research claims.
Ayro generates paper recommendations based on positive and negative example papers. The customer discovers related research tailored to their specific interests.
Each card is one request a support team gets, and the Semanticscholar actions Ayro runs to close it.
Ayro searches by topic when the question is thematic, matches the closest title when only a fragment is remembered, and falls back to searching the body text of papers.
Ayro opens the paper record, lists the works citing it to gauge its impact, and reads its bibliography to reconstruct the scholarly context it was written in.
Ayro resolves a plain-text name to an author record, reads their affiliations, paper count, citation count, h-index, and ORCID, and lists what they have published.
Ayro requests recommendations from positive and negative example papers, then pulls the details for the whole resulting set in a single batched call.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Semanticscholar actions it has and picks the ones a request needs.
Authorize the Semanticscholar account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Semanticscholar actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeSemanticscholar · Ayro
What can you do in Semanticscholar without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Semanticscholar.
Text snippet search matches a natural-language query against paper titles, abstracts, and body text, returning excerpts of roughly 500 words ranked by relevance. That gives Ayro a passage it can quote and attribute rather than a title whose contents it would have to assume.
All 20 actions your agent can call on Semanticscholar, straight from the live MCP connection.
Retrieve detailed information about an author from Semantic Scholar, including name, affiliations, publication statistics (paperCount, citationCount, h-index), external IDs (ORCID, DBLP), and optionally papers.
Retrieves a list of papers authored or co-authored by a specific researcher identified by their unique Semantic Scholar author ID.
Examples: <ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b</code></li> <ul> <li>Returns a paper with its paperId and title.
Retrieves the list of authors for a specific paper identified by its unique paper_id in the Semantic Scholar database.
Retrieves a list of citations for a specific academic paper using its unique Semantic Scholar paper ID.
Retrieves the list of references cited by a specific paper in the Semantic Scholar database.
Get download links for a specific dataset within a release.
Get download links for incremental diffs between dataset releases.
Retrieves detailed information for multiple authors from Semantic Scholar in a single API call.
Retrieve detailed information for multiple academic papers in a single API call using the Semantic Scholar paper batch endpoint.
Get paper recommendations based on positive and negative example papers.
Get recommended papers for a single positive example paper.
Retrieve metadata for a specific Semantic Scholar dataset release.
List all available dataset releases from Semantic Scholar.
Behaves similarly to <code>/paper/search</code>, but is intended for retrieval of a single paper based on closest title match to given query.
Perform bulk search for academic papers.
Search for academic authors in the Semantic Scholar database by name.
Search for academic papers by relevance in the Semantic Scholar database.
Get autocomplete suggestions for paper queries.
Search for text snippets (~500 words) within academic papers that match your natural language query.
Same connection, same setup. Pick the next one your team already uses.
Compares model pricing and limits, parses documents, transcribes audio, redacts personal data, and reports what past calls cost.
Transcribes recorded audio into text, speaks answers back through text-to-speech, and reports project usage so spend stays visible.
Renders videos from saved templates, tracks render status and remaining credits, files assets into folders, and drives live streaming avatars.
Runs chat and agent completions, transcribes audio, extracts text from scanned documents, and keeps a RAG document library up to date.
Runs a vision workflow on demand, validates a specification before it executes, and reports inference server health and metrics.
Opens calls with their cost and duration, changes assistant voice and model settings, provisions phone numbers, and runs call analytics.

Authorize the account and your agent has all 20 actions from the first conversation.
