FreeHow credits work →

AI for literature reviews

Search real papers across seven indexes, remove retracted ones and keep every citation checkable, without leaving your agent.

Connect your agentSee all capabilities
Literature reviewGrant writing

Capabilities for a literature review

In the order of the work: search, screen out retracted papers, check the citations you keep, then add trials and data.

Search papers

Search papers

All disciplines · OpenAlex, PubMed / Europe PMC, arXiv +5

Retraction checker

Retraction checker

All disciplines · Retraction Watch, Crossref

Verify references

Verify references

All disciplines · Crossref, OpenAlex

Clinical trials search

Clinical trials search

Life sciences & medicine · ClinicalTrials.gov

Find datasets

Find datasets

All disciplines · DataCite, Zenodo, Dryad +2

Search papers
One de-duplicated search over OpenAlex, PubMed, arXiv, bioRxiv, DBLP, INSPIRE and ERIC.
Retraction checker
Screen the included papers before you synthesise them.
Verify references
Confirm that every citation in the draft points to a real paper with the right details.
Clinical trials search
For health topics: registered trials from ClinicalTrials.gov, including ones with no publication.
Find datasets
Data behind the papers, for a meta-analysis or a secondary analysis.

Requests during a literature review

Search papers

You say to your agent

Search for randomised trials and reviews on intermittent fasting and type 2 diabetes, 2015 to now. Give me a table with DOI and study type.

De-duplicated records from several indexes with DOI, authors, venue and citation counts.

Retraction checker

You say to your agent

These 60 DOIs passed my screening. Remove any that have been retracted and list corrections separately.

Retraction and correction notices with dates and links, so you can record the exclusions.

Clinical trials search

You say to your agent

Are there completed phase 3 trials on this question registered at ClinicalTrials.gov that are missing from my list?

Trials with NCT ID, phase, status, sponsor and outcomes.

Why an agent, not another app?

You already write and think with Claude or ChatGPT. There is no other app to switch to: you add academic data tools to the agent you have.

Over MCP (Model Context Protocol) the agent queries academic databases directly, and the records it gets back carry their source and licence, so you can check them.

Frequently asked questions

It is one documented source among several. The search covers OpenAlex, PubMed, arXiv, bioRxiv, DBLP, INSPIRE and ERIC. Subscription databases such as Embase or Scopus are not included, so a protocol that requires them still needs a separate search.

By DOI, against Retraction Watch and Crossref. You get the notice type, date, reason and link. Papers without a DOI, or with problems nobody has reported, are not caught.

ScholarMuse returns records and, where one exists, a link to an open-access copy. What your agent then reads and summarises depends on the agent. Paywalled full text is not provided.

Every call your agent makes uses credits, and a call is charged only when it succeeds. There are no subscriptions. A new account starts with a one-time gift of 50 credits. The 6 web tools under /tools are free without an account, up to 5 runs a day.

Requests are used only to answer you. We do not train models on them.

Ready to make your agent a better scholar?

Connect once. Papers, data and figures from 50+ sources, in the agent you already use.

Works with compatible AI agents

ClaudeChatGPTCodexCursorWorkBuddyTraeGemini CLIAntigravityQoderCodeBuddyKimi CodeQwen CodeClineKiroWindsurfZedOpenCodeOpenClawDifyCherry StudioLM StudioGooseAmpContinueRoo CodeVS CodeJetBrainsWarpRaycastCopilotPerplexityAny MCP client

Data from OpenAlex · Crossref · PubMed · arXiv · NIH · UniProt · PDB · PubChem · NASA · World Bank · USGS · GBIF and more