FreeHow credits work →

AI tools for PhD students

For the years between a first literature search and a submitted thesis: your agent searches real papers, checks every reference, finds data and draws the figures.

Capabilities for a thesis

Ordered the way a thesis usually goes: read the field, keep the reference list clean, find data, then draw figures and choose a journal for the first paper.

Search papers
The literature chapter starts here: one search over seven indexes, with links to open-access copies.
Verify references
A thesis has hundreds of references. Each one is checked against Crossref, OpenAlex and PubMed before your committee reads it.
Retraction checker
Papers you cited in year one may have been retracted by the time you submit.
Find datasets
Open data for a pilot analysis or a replication, with licence and DOI.
Economic & social statistics
Official series for background sections and for empirical chapters in economics and social science.
Scientific figure maker
Schematics of your mechanism, study design or workflow for the thesis and for talks.
Journal checker
Before a first submission: is the journal listed in DOAJ, and what does it charge?
Graphical abstract maker
For journals that ask for a graphical abstract with the manuscript.

Requests from a PhD student

Search papers

You say to your agent

Find review articles and the most cited papers since 2019 on soil microbiome response to drought. Open access first.

Records with DOI, authors, venue and citation counts, plus open-access PDF links where they exist.

Verify references

You say to your agent

Here is the reference list of chapter 2. Check every entry and tell me which ones you cannot find or have a wrong year, volume or DOI.

Each entry comes back as verified, corrected or not found, with the matched record and its DOI.

Find datasets

You say to your agent

Find open datasets with long-term soil moisture measurements in grasslands that I may reuse in my thesis.

Datasets with repository, size, format, licence and DOI, so you can see what reuse is allowed.

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

No. ScholarMuse gives your agent real records to work from: papers, DOIs, retraction notices. Reading them and making the argument stay with you. A reference check confirms that a paper exists and its details are right, not that it supports your claim.

No. Search results link to an open-access copy through Unpaywall when one exists. For everything else you still need your library’s access.

Yes. Tools are grouped into discipline packs, for example life sciences, chemistry and materials, and earth and environment. You choose the packs when you authorize your agent and can change them later.

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