Used as a novelty-check source: the server queries arXiv to check whether a claim (e.g. a new variable star or planet candidate) has already been reported in a preprint, and logs the dated result as found/not-checked.
Used as a novelty-check source that searches GitHub repositories for hobbyist postings or other people's verification repos covering the same object or claim.
Provides novelty and catalog checks against NASA data and services, including NASA ADS (with an API token) and the NASA Exoplanet Archive for known planets and TOIs; NASA TESS data is also the source for planet-candidate and variable-star hunts.
Used both as a novelty-check source (searching preprints, data and predictions already deposited) and for preregistration: it can create a Zenodo draft with a reserved DOI for frozen predictions, without ever publishing it on the user's behalf.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Discover Anything start a hunt for new variable stars in recent TESS sectors"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent skills + a CLI + an MCP server that turn "AI found something" into a claim experts can check.
Quick start · What the tools enforce · Skills · Domains · FAQ
In one week in October 2026, people with coding agents and no institutional affiliation found transiting-planet candidates in NASA TESS data, a meteorite fall that no catalogue records in an 1812 newspaper, and three Javan rhinoceroses missing from the historical record in Dutch East India Company letters. The data had been public for years.
Finding a candidate is now cheap. The first question every expert asked was the same: "How are you ruling out known objects, noise and impostors?" The credible hunters answered with the same practices, worked out independently: recover known answers first, measure the false-alarm rate, check the primary record, search every catalogue, preregister, and let a fresh mind attack the result.
Discover Anything packages that discipline so any coding agent follows it, and checks that it did, instead of taking the agent's word for it.
pip install "discover-anything[mcp] @ git+https://github.com/karangupta8/discover-anything"
discover setup --yes # installs the skills and registers the MCP server (Claude Code)Skills only, for any agent that supports the open Agent Skills format:
npx skills add karangupta8/discover-anythingThen ask your agent:
Use find-a-gap. I have a laptop and a weekend. Suggest three gaps in public data I could work on.Use discover-anything to start a hunt for new variable stars in recent TESS sectors.Use vet-a-claim on this before I post it: <link or folder>Related MCP server: nanoGentzen
Every hunt gets a folder and an append-only evidence ledger. The agent works; the tools keep score.
$ discover new tess-variables --domain astronomy
$ discover status
[ PASS] 0 Curiosity
[ PASS] 1 Gap
[ PASS] 2 Scope
[ FAIL] 3 Calibrate
no 'null' evidence: run the pipeline on inverted or shuffled data, then `discover record <file> --tag null`
no 'injection' evidence: plant synthetic signals and record the recovery with `--tag injection` (or the human waives it with a reason)
frozen settings settings.yml changed since freezing; re-freeze with a reason and re-run the null test
1 evidence entries tagged 'known-answer'
[ FAIL] 4 Search
...
Next: no 'null' evidence: run the pipeline on inverted or shuffled data, then `discover record <file> --tag null`And the novelty check, run on the October 2026 planet candidate TIC 4206066:
$ discover novelty run --claim TIC-4206066 --id "TIC 4206066" --ra 80.859827 --dec -1.326974
E-001 wrote novelty/TIC-4206066_2026-10-14T143012Z.md
found: 4, none: 9, not-checked: 1, manual: 0, n/a: 0
[found] SIMBAD (identifier): 1 record(s) ← listed as StKM 1-561
[found] SIMBAD (cone): 1 record(s)
[not-checked] NASA ADS: ADS_API_TOKEN is not set
[found] Zenodo (preprints, data, predictions): 5 record(s)
[found] GitHub repositories (hobbyist postings): 1 record(s) ← someone else's verification repoRule | How it's checked |
Numbers come from files |
|
Calibrate before searching | Gate 3 needs evidence tagged |
No moving the goalposts |
|
Show the funnel |
|
Is it new? |
|
Fresh-eyes review |
|
Preregister |
|
Humans make the human calls | Waivers and attestations ("an expert has seen it") are CLI-only and are not exposed to agents over MCP |
Astronomy | Literature and hobbyists | Historical |
SIMBAD (identifier and cone) · AAVSO VSX · TESS eclipsing binaries (Prša+ 2022) · Gaia DR3 variability · Gaia DR3 non-single stars · APOGEE binaries · NASA Exoplanet Archive (planets, TOIs) · ExoFOP-TESS | arXiv · NASA ADS (token) · Zenodo · GitHub | Smithsonian Global Volcanism Program · Meteoritical Bulletin (manual) · any source you add with |
Controls: inverted and time-shuffled nulls, block shuffle for red noise, box-transit injection-recovery, hold-out prediction, known-answer scoring with period aliases
Vetting: odd/even depths, secondary eclipse, per-season depth consistency, single-event dominance, known systematic periods, Lomb-Scargle with false-alarm probability
Archives: reprint grouping (so one story printed in ten papers counts once), judge-model agreement (accuracy, kappa, confusions) before a cheap model filters a corpus
Skill | Use it to |
Run a hunt end to end: nine phases with gates, evidence rules, domain packs | |
Choose what to look for: gaps sized for one person, with known answers to calibrate on | |
Stress-test your own or someone else's find before it is posted or believed | |
Answer "has anyone found this already?" systematically, with a dated log | |
Make a candidate falsifiable before the telescope looks again |
Domain | Examples | Pack |
Astronomy | Planet candidates, variable stars, eclipsing binaries, asteroid rotation periods | |
Historical archives | Meteorite falls, volcanic eruptions, animal records, lost ships in digitised letters, newspapers and logbooks | |
Your field | Anything with public data, known answers to calibrate on, and a specialist who can confirm | Core loop; your |
Scientific Agent Skills gives agents broad scientific capability: libraries, databases, analysis and writing, mostly for professional life-science work. Discover Anything is narrower: the discipline for turning public data into a discovery claim, with checks the agent can't skip. Use both: their skills for the analysis, these gates for the claim.
No. You need curiosity and the willingness to believe a control over your own
excitement. discover status always tells you the next step, and the skills
say which decisions are yours.
It is designed to do the opposite. Nothing reaches an official channel until it has passed known-answer recovery, a measured false-alarm rate, a primary-record check, a dated novelty search, adversarial review and a human expert's eye. Most candidates die on the way, and the rejections are kept.
No. Say "found with an AI coding agent, reviewed by a second model and a fresh session". Say "candidate" until an expert or catalogue accepts it.
It can write a file called null.json. It can't make that file match a hash
recorded before the threshold changed, pass check-claims with uncited
numbers, or attest that an expert reviewed it. The tools make shortcuts
visible; the human still reads every plot.
The tools are free and run locally. In 2026, a 526-star planet search ran in one morning on a $100/month agent plan, and a small model read 59,000 archive passages for about $3.
Public work from October 2026: three independent TESS planet hunts (origins) and two investigations of the Dutch East India Company archive (origins). Credit to Pavel Rabtsevich, Eumemic and Paras Chopra (TESS), and Benjamin Breen and Jesse Waites (archives; see Waites's Antiquity). The skills-plus-tools shape follows REA. Sources: docs/sources.md.
Most wanted: novelty connectors for catalogues in your field, controls and vetting tests for a data type, and domain packs. See CONTRIBUTING.md.
This server cannot be deployed
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Governance layer for AI coding agents: knowledge-graph grounding, session audit, policy controls.
Expert review for AI agents. On-chain proof of human review.
