mooltrace

For teams shipping health AI

Your AI cites a page.
That page cites a review.
The review rests on a retracted trial.

MoolTrace builds a citation graph in FalkorDB from the answer, through each page and review, down to the trials. It blocks the answer if a source it relies on was retracted, warns on an Expression of Concern, shows you the exact path, and drafts a fix.

A citation check passes all 35 Harvard nutrition pages.

MoolTrace flags 2, and I checked both by hand.

Not in the graph? MoolTrace says “not checked”, never “safe”.

Page

Harvard vitamin D

Review

Cochrane 2014 (Avenell)

Trial

Ishida 2004
Retracted · May 2025

Live · Harvard vitamin D page

Watch it catch one.

Page

Harvard vitamin D

checking…

Following citations…

At 1 hop the page looks clean: nothing it cites directly is flagged.

2 of 35

A citation check passes all 35 — MoolTrace flags 2.

Harvard nutrition pages that rest on withdrawn or retracted research. I checked both by hand.

Zinc for the common cold

Review · Cochrane 2011 (Singh) · cited by Harvard zinc

Withdrawn by Cochrane in April 2015 over concerns about the calculation and analysis of data.

Withdrawn by Cochrane · 2015
Vitamin A, nothing flaggedVitamin D, rests on withdrawn or retracted researchVitamin E, nothing flaggedVitamin K, nothing flaggedVitamin C, nothing flaggedVitamin B6, nothing flaggedVitamin B12, nothing flaggedFolic acid, nothing flaggedCalcium, nothing flaggedSalt and sodium, nothing flaggedPotassium, nothing flaggedCopper, nothing flaggedIodine, nothing flaggedZinc, rests on withdrawn or retracted researchVitamin B1, nothing flaggedRiboflavin vitamin B2, nothing flaggedNiacin vitamin B3, nothing flaggedPantothenic acid vitamin B5, nothing flaggedBiotin vitamin B7, nothing flaggedCholine, nothing flaggedChloride, nothing flaggedChromium, nothing flaggedFluoride, nothing flaggedIron, nothing flaggedMagnesium, nothing flaggedManganese, nothing flaggedMolybdenum, nothing flaggedNickel, nothing flaggedPhosphorus, nothing flaggedSelenium, nothing flaggedVegetables and fruits, nothing flaggedWhole grains, nothing flaggedProtein, nothing flaggedTypes of fat, nothing flaggedMultivitamin, nothing flagged
Rests on withdrawn or retracted research (MoolTrace flags it) Nothing flagged (both checks pass)Click a tile to check that page.

Every page linked from Harvard's Vitamins & Minerals index · checked 17 Oct 2026 · each hit verified by hand

How it works

What goes in, what the graph does, what comes out.

In

Your answer

“Vitamin D prevents fractures.” Source: Harvard

A draft, its links, or a call from your agent.

The graph · FalkorDB

Page

Harvard vitamin D
mentions 0.55

Review

Cochrane 2014 (Avenell)
uses its data 0.85

Trial

Ishida 2004
flagged by

Notice

Retracted · May 2025
Retracted

strongest chain: 0.55 × 0.85 = 0.47, found with algo.SPpaths

Out

✕Don't ship

Rests on research retracted in May 2025, 2 hops down. The path and the sentence behind each hop come with it.

The fix

Harvard reviews the evidence at nutritionsource.hsph.harvard.edu/vitamin-d.

An earlier version of this answer cited the Harvard Nutrition Source page “Vitamin D”, which cites Avenell et al. 2014, which uses data from Ishida et al. 2004, a paper that was retracted in May 2025, so that source was removed.

  1. 1

    You give it an answer

    Paste a draft or the links it cites. Or let your agent call it over MCP.

  2. 2

    It builds the graph

    Every page gets resolved to the papers behind it (Crossref, OpenAlex, PubMed) and stored in FalkorDB as page, review and trial. Retractions and concerns hang off the papers they flag.

  3. 3

    It weighs every link

    A trial the review actually included counts fully. A passing mention barely counts. FalkorDB's shortest path search finds the strongest chain to a flagged paper.

  4. 4

    You get a verdict

    Don't ship, Review, Clear or Not checked. Always with the path and the sentence behind each hop.

  5. 5

    It fixes the answer

    Only the sentence that leaned on the bad source changes. Then it checks the answer again.

Checking only the answer's own citations: looks fine
Walking the citation graph: don't ship

Track 01 · Agents that act on connected data

Works where answers get made.

Your agent checks itself.

The model picks the tools. The graph decides. Only tool output ships.

  1. check_answer · don't ship

    Walks page → review → trial in FalkorDB.

  2. explain_path · Harvard → Cochrane → Ishida

    Shows the exact chain and the sentence behind each hop.

  3. rewrite_answer · fixed, clear

    Removes the retracted source, then checks again.

Without MoolTrace · ships as written

Vitamin D helps prevent fractures in older adults. Harvard reviews the evidence at nutritionsource.hsph.harvard.edu/vitamin-d.

With MoolTrace · checked again: clear

Vitamin D helps prevent fractures in older adults (no checked source remains for this claim). An earlier version of this answer cited the Harvard Nutrition Source page “Vitamin D”, which cites Avenell et al. 2014, which uses data from Ishida et al. 2004, a paper that was retracted in May 2025, so that source was removed.
Run the agent on this draft

Any agent, over MCP.

Point Claude, Cursor or your own agent at the remote endpoint.

https://mooltrace.h9g8gwz2b559t.ap-south-1.cs.amazonlightsail.com/mcp
check_answerwhat_rests_onrecheck_affected

CI blocks the PR.

Fail the build when an answer rests on a retracted source.

mooltrace batch --fail-on block

exit 1

Retractions arrive later.

When a paper is retracted, find every shipped answer that rests on it.

Trial · Ishida 2004 · Retracted
← Review · Cochrane 2014 (Avenell)
← Page · Harvard vitamin D
← stored answers citing it

Try the retraction alert →

0 → 31 of 40

reviews distorted by retracted trials (BMJ 2025 answer key): a DOI check finds 0, MoolTrace reaches the trial in 31

0.43 → 1.00 recall

on 52 labelled answers, DOI-only check vs MoolTrace

2 of 35

Harvard nutrition pages rest on withdrawn or retracted research

Check the roots before you ship.