MCP.Market

Starfetch MCP server

by starfetch-js·io.github.starfetch-js/starfetch·v0.3.0·2 stars
No reviews yet

Query public astronomy catalogs through metadata-first TAP and ADQL tools.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

2 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Starfetch yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Starfetch tools (12, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • starfetch_list_presets

    List built-in TAP service presets before selecting an explicit target for metadata inspection.

  • starfetch_registry_search

    Search VO registry metadata when no built-in preset fits; inspect the selected service before querying it.

  • starfetch_tap_availability

    Check whether the selected TAP service reports itself available; an unavailable service is not an empty catalog result.

  • starfetch_tap_capabilities

    Inspect the selected TAP service's languages, formats, and authentication requirements before using service-specific features.

  • starfetch_tap_columns

    Inspect names, datatypes, units, and descriptions for an exact metadata-discovered table before constructing ADQL.

  • starfetch_tap_job_deletewrite action
  • starfetch_tap_job_fetch
  • starfetch_tap_job_status
  • starfetch_tap_job_wait
  • starfetch_tap_querywrite action

    Run a small bounded synchronous TAP ADQL query after inspecting the exact table and columns. Use TOP in ADQL and/or maxrec, and treat tool errors as failures rather than empty scientific results.

  • starfetch_tap_submit_jobwrite action
  • starfetch_tap_tables

    List tables on the selected TAP service before choosing an exact table for ADQL.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

1 medium
  • Code scan3 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 16 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/index.js: …s("Cloudflare")) return false; try { new Function(""); return true; } catch (_) { ret…
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Starfetch compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 65% of 48,255 servers
Tools
12
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 75% of 28,688 servers
Downloads a week
45
more than 37% of 12,191 servers with a package

What its tools let an agent do: 9 read · 3 change

Install Starfetch in Claude Code, Cursor or VS Code

Runs npx -y @starfetch-js/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add starfetch -- npx -y @starfetch-js/mcp
Add to Cursor

What the publisher says

From the Starfetch repository's README, as published. We do not edit it. Read it on GitHub

Starfetch

Starfetch gives AI agents safe, reproducible access to public astronomy catalogs through the Model Context Protocol (MCP).

Ask an astronomy question in natural language. A Starfetch-enabled agent can select an appropriate service, inspect its live tables and columns, construct a bounded ADQL query, execute it, and return the result with the exact service, table, query, limit, units, and assumptions it used.

You: Find the 10 Gaia DR3 sources with the highest proper motion within 0.5
     degrees of the Pleiades center at RA 56.75°, Dec +24.12°. What stands out?

Agent: selects Gaia → inspects metadata → runs bounded ADQL →
       returns catalog rows, exact ADQL, units, and assumptions

Representative captured result:

Service: ESA Gaia Archive
Table: gaiadr3.gaia_source
Rows returned: 10
Query limit: TOP 10 / MAXREC 10

Highest returned proper motions:
- Gaia DR3 66780900298410496: 244.48 mas/yr
- Gaia DR3 66524409149512064: 184.50 mas/yr

Exact ADQL:
SELECT TOP 10 source_id, ra, dec, pm, pmra, pmdec, parallax, parallax_error,
  phot_g_mean_mag, bp_rp, ruwe
FROM gaiadr3.gaia_source
WHERE CONTAINS(POINT('ICRS', ra, dec), CIRCLE('ICRS', 56.75, 24.12, 0.5)) = 1
  AND pm IS NOT NULL
ORDER BY pm DESC

Gaia, SIMBAD, VizieR, the NASA Exoplanet Archive, and IRSA are available as built-in service presets. Agents can also discover and query other public TAP services by URL. Starfetch remains TAP-native and keeps ADQL visible, so the agent workflow is convenient without becoming a scientific black box.

Start here

  • Connect an agent
  • What the agent does
  • Why Starfetch?
  • Reliability without hidden assumptions
  • Optional Starfetch skill
  • Supported scope
  • CLI and TypeScript
  • Run the Gaia proper-motion demo
  • Development

Connect an agent

The local npm server is Starfetch's stable public connection path. It runs on your computer and can be registered with any compatible MCP client.

Local npm server

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Starfetch: common questions

Is Starfetch MCP server safe?
Mostly: it is graded B (83/100). Read the Starfetch safety report
How do I install Starfetch?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Starfetch need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Starfetch maintained?
The last commit was 57 days ago (2026-09-08). The latest release is v0.3.0.
How does Starfetch compare with other MCP servers?
safety score 83/100 (higher than 65% of 48,255 servers); tools 12 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.