Hosted and managed by the University of Alabama in Huntsville

Agentarium

scientific agent registry
ToolsGovernanceSign in with ORCID

Astro Data Search Agent

v1.0.0active

Astrophysics dataset discovery agent for finding astronomical data across NASA archives (MAST, HEASARC, IRSA) via Astroquery and ADS. Supports object-based, coordinate-based, and event-driven search patterns for researchers at all experience levels. Outputs are delivered via a structured schema and interactive chat with the user for clarification, guidance, approval gates, or status updates.

by NASA-IMPACT akd-ext contributors (NASA-IMPACT) · astrophysics · search-retrieval

T1 · Conformantwhat's this?
tested on
gpt-5.2
license
Apache-2.0
framework
openai-agents-sdk
citable url
https://agentarium.science/a/astro-search-care/v/1.0.0
Guardrails & validationexplicitly declared by the author — shown so you can judge, not registry-verified

Guardrails declared — author-stated

✓
Non-prescriptive
Never claims a dataset is 'best' or scientifically optimal — only surfaces candidate datasets with metadata context.
✓
No download automation
Never executes download scripts or provides automated data retrieval code.
✓
Scope expansion gate
Never adds new archives or relaxes search constraints without explicit user permission.
✓
No fabrication
Never fabricates observation IDs, URLs, or endpoints; all claims grounded in actual search results.
✓
No guessing critical parameters
Never guesses observation times, exposure requirements, calibration levels, or proprietary dates.
✓
Proprietary data disclosure
Includes proprietary datasets in results but clearly labels them; never suggests unauthorized access.
✓
Non-NASA archive gate
Does not target ESO, ESA-primary, or CDS archives without explicit user request and acknowledgment.

Validation methodology — author-stated

Tested50 known Earth-science queries with ground-truth CMR concept IDs (seed-record placeholder).
DataCurated query set from NASA-IMPACT teams (seed-record placeholder).
MetricReference collection appears in ranked top-5 (seed-record placeholder).
ResultSeed record — author should publish a real validation before public release.
CaveatThis is a registry seed record; the validation block was filled with placeholders. The author is encouraged to submit a new version with real numbers and a real caveat.
Required tools — live healthlive status of MCP endpoints this agent depends on; not registry-verified
astroquery_mcp_serverapproval: never
missing from registry

allowed: astroquery_list_modules, astroquery_list_functions, astroquery_get_function_info, astroquery_check_auth, astroquery_execute, ads_query_compact, ads_get_paper

Reproductionsindependent runs by other scientists — Tier 5 trigger
Ran this agent yourself? File an independent reproduction — it can move the listing to Tier 5.Sign in to reproduce
Other disclosuresas described by the author
Intended use
Helps astrophysics researchers (from undergraduates to postdoctoral scientists) discover candidate astronomical datasets in NASA archives (MAST, HEASARC, IRSA) before formal analysis pipelines. Built for exploratory, human-in-the-loop discovery — the user retains control over scientific framing, constraint relaxation, archive expansion, and final dataset selection.
Out of scope
Does not recommend, select, or endorse datasets as scientifically optimal. Does not execute download scripts or automate data retrieval. Does not target non-NASA archives (ESO, ESA-primary, CDS) without explicit user request. Does not assess scientific fitness, data quality, or interpret results. Not for proprietary/restricted data access. Does not guess critical metadata such as observation times, exposure requirements, or calibration levels.
Known failure modes
Object name resolution via SIMBAD may return multiple ambiguous matches requiring user disambiguation. The locate_data function is not directly exposed in MCP tools (see Data Product URLs workaround). Event/alert localizations are labeled "best-available" and may be imprecise. Archive coverage gaps may yield sparse results for rare targets or narrow time windows. Non-NASA archives are not queried by default, which may miss relevant datasets.
Worked example

input

Find X-ray observations of Crab Nebula

output

Resolving "Crab Nebula" via SIMBAD...
→ Canonical name: M 1 (PSR B0531+21), RA=83.6287, Dec=+22.0147 (ICRS)

Searching HEASARC for X-ray observations at these coordinates (radius 5 arcmin)...

Candidate datasets found:

**Chandra (chanmaster)**
- ObsID 1244 | Instrument: ACIS-S | Exposure: 29.7 ks | Start: 2000-09-18 | Public | Level 2
  Access: https://heasarc.gsfc.nasa.gov/FTP/chandra/data/byobsid/4/1244/
- ObsID 8482 | Instrument: HRC-S | Exposure: 28.1 ks | Start: 2007-11-08 | Public | Level 2

**XMM-Newton (xmmmaster)**
- ObsID 0153750101 | Instrument: EPIC-PN | Exposure: 22.0 ks | Start: 2003-02-14 | Public

Found 3 candidate X-ray datasets. Would you like me to also search for NuSTAR or Swift
observations, or retrieve data product URLs for any of these?
What this listing is. A structured, format-conformant submission, screened for topic and obvious safety issues. The registry does not verify that the agent is correct, that it works, or that the author's disclosures are accurate. Evaluate before relying on it for research.