FreeHow credits work →

AI for grant writing

See what has been funded on your topic, by whom and for how much. Then support the case with papers and official statistics, and draw the figures.

Connect your agentSee all capabilities
Literature reviewGrant writing

Capabilities for a grant proposal

Following the sections of a proposal: what is already funded, the evidence for the need, the figures, and a clean reference list.

Find funded grants

Find funded grants

All disciplines · NIH RePORTER, NSF Awards, UKRI Gateway to Research

Search papers

Search papers

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

Economic & social statistics

Economic & social statistics

All disciplines · FRED, World Bank, IMF +5

Scientific figure maker

Scientific figure maker

All disciplines · Best-in-class figure model

Verify references

Verify references

All disciplines · Crossref, OpenAlex

Find funded grants
Funded projects on your topic with amounts and abstracts: what the funder has already paid for, and where the gap is.
Search papers
Recent papers for the background and significance section, with DOIs you can cite.
Economic & social statistics
Official figures for the size of the problem, with unit and source.
Scientific figure maker
An overview figure of the aims, or a schematic of the approach.
Verify references
Check every reference before submission; reviewers do look them up.

Requests while writing a proposal

Find funded grants

You say to your agent

What has NIH funded on antimicrobial resistance in wastewater since 2020? Give me PI, institution, amount and a one-line summary of each abstract.

Funded projects with project number, PI, institution, year and amount, and their full abstracts.

Economic & social statistics

You say to your agent

I need numbers for the significance section: health spending as a share of GDP in OECD countries, 2010 to the latest year.

A date and value series with unit and source, ready to cite or plot.

Scientific figure maker

You say to your agent

Draw an overview of the project: three aims in a row, each with its method and expected result. Plain style for a single-column page.

A labelled schematic you can adjust with follow-up instructions.

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. It searches projects that were funded by NIH, NSF and UKRI. Calls, eligibility rules and deadlines come from the funder.

Which questions a funder has supported, how large typical awards are, who works on neighbouring topics, and how successful abstracts are framed. Your agent can compare those abstracts with your draft aims.

Yes. Series come from FRED, the World Bank, IMF, OECD, Eurostat, BLS, the US Census Bureau and Our World in Data, and each one carries its source, unit and licence.

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