Atlas / MCP servers / programcomputer / NASA Data Interface

NASA Data InterfaceSAFE

Name: NASA Data Interface
Author: programcomputer

mcp/programcomputer/nasa-data-interface

MCP server by programcomputer · Audited 2026-10-07

A Model Context Protocol (MCP) server for NASA APIs, providing a standardized interface for AI models to interact with NASA's vast array of data sources.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

47 44r · 3w · 0d

Transport

stdio · streamable-http

License

ISC

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/@programcomputer/nasa-mcp-server)

A Model Context Protocol (MCP) server for NASA APIs, providing a standardized interface for AI models to interact with NASA's vast array of data sources. This server implements the official Model Context Protocol specification.

Big thanks to the MCP community for their support and guidance!

Features

Access to 20+ NASA data sources through a single, consistent interface
Standardized data formats optimized for AI consumption
Automatic parameter validation and error handling
Rate limit management for NASA API keys
Comprehensive documentation and examples
Support for various NASA imagery formats
Data conversion and formatting for LLM compatibility
Cross-platform support (Windows, macOS, Linux)

Example prompts

Ask your MCP client things like:

"Show me today's Astronomy Picture of the Day and explain what it shows."
"Were there any solar storms in September 2026: strong flares, Earth-directed CMEs or geomagnetic storms?"
"Which asteroids fly past Earth today, and which one comes closest?"
"Will any asteroid pass closer to Earth than the Moon in the next 90 days?"
"What are the odds that Bennu hits Earth, according to JPL Sentry?"
"Find NASA photos of the Apollo 11 lunar module taken in 1969."
"Which tropical storms and hurricanes are active right now?"
"Show me a detailed satellite view of the Nile Delta and the Sinai on 2025-07-15."
"Find cloud-hosted sea ice concentration datasets in NASA Earthdata."
"What were the daily highs, lows and solar energy in Denver during the first week of July 2025?"
"List the nearest roughly Earth-sized, temperate exoplanets discovered since 2020."
"Where was the ISS over the Earth between 00:00 and 00:10 UTC on 2026-09-29?"
"Get the latest t

Read from source at commit 052dbeb92799OBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add nasa-mcp-server --env FIRMS_MAP_KEY=${FIRMS_MAP_KEY} -- npx -y @programcomputer/[email protected]

claude-desktop

{
  "mcpServers": {
    "nasa-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@programcomputer/[email protected]"
      ],
      "env": {
        "FIRMS_MAP_KEY": "${FIRMS_MAP_KEY}"
      }
    }
  }
}

Exposed tools (47)

44 read · 3 write · 0 destructive.

Tool	Risk	Description
`body`	read	Body (default Earth)
`collection`	read	Image collection (
`date`	read	Date of the picture (YYYY-MM-DD); defaults to the latest
`date_max`	read	End date (YYYY-MM-DD)
`date_min`	write	Start date (YYYY-MM-DD)
`dist_max`	read	Maximum distance, e.g. 0.05 (au) or 10LD
`end_date`	read	End of a date range (YYYY-MM-DD)
`energy_min`	read	Minimum radiated energy (1e10 J)
`jpl-sbdb`	read	SBDB record for an asteroid or comet name/designation, fetched on read.
`jpl_cad`	read	Asteroid and comet close approaches to the planets, past and future, from the JPL SBDB Close-Approach Data API.
`jpl_fireball`	read	Fireball (bolide) events reported by US Government sensors, from the JPL Fireball API.
`jpl_horizons`	read	Ephemerides and object data for solar-system bodies from the JPL Horizons API (GET).
`jpl_horizons_file`	write	Same as jpl_horizons, but submits the parameters as a Horizons input file (POST to horizons_file.api).
`jpl_jd_cal`	read	Convert between Julian dates and calendar dates (UTC) with the JPL JD-Calendar API.
`jpl_mission_design`	read	Ballistic mission options to asteroids and comets from the JPL Small-Body Mission Design API. Object mode (des, spk or sstr) returns the pre-computed
`jpl_nhats`	read	Near-Earth objects accessible to human missions (NHATS): a constrained summary list, or one object by des/spk.
`jpl_periodic_orbits`	read	Periodic orbits (halo, DRO, Lyapunov, ...) in three-body systems from the JPL Three-Body Periodic Orbits database.
`jpl_sbdb`	read	Orbital and physical data for one asteroid or comet from the JPL Small-Body Database (SBDB).
`jpl_scout`	read	JPL Scout trajectory analysis and hazard assessment for unconfirmed objects on the Minor Planet Center NEO Confirmation Page.
`jpl_sentry`	read	Earth impact risk assessments from JPL Sentry: summary table, one object, virtual impactors, or removed objects.
`nasa-apod`	read	APOD metadata (title, explanation, image or video URL) for a date, or the latest picture when date is empty, fetched from science.nasa.gov on read. No API key needed.
`nasa-epic`	read	DSCOVR EPIC image metadata for a date and collection (natural or enhanced), fetched on read.
`nasa_apod`	read	NASA
`nasa_cmr`	read	Search NASA\
`nasa_donki`	read	Space Weather Database Of Notifications, Knowledge, Information (DONKI) events by type for up to 30 days at a time, from the NASA CCMC DONKI API
`nasa_eonet`	read	Natural events (wildfires, storms, volcanoes, ice, ...) from the Earth Observatory Natural Event Tracker. Filters are sent exactly as given; no automatic broadening.
`nasa_epic`	read	Earth Polychromatic Imaging Camera (DSCOVR) full-disc Earth images for a day: metadata for every image plus a bounded number embedded.
`nasa_exoplanet`	read	Query the NASA Exoplanet Archive through its TAP service (ADQL). Tables use current TAP names such as ps, pscomppars, cumulative and toi.
`nasa_firms`	read	Active fire/thermal anomaly detections from NASA FIRMS for a bounding box and 1-5 day window. Requires FIRMS_MAP_KEY (not NASA_API_KEY).
`nasa_gibs`	read	Render a Global Imagery Browse Services (GIBS) layer for a date and bounding box as an image (WMS GetMap, EPSG:4326).
`nasa_images`	read	Search NASA
`nasa_insight_weather`	read	HISTORICAL DATA ONLY: per-sol Mars surface weather (air temperature, pressure, wind) from NASA
`nasa_mars_rover`	read	DEPRECATED: the upstream Mars Rover Photos API (api.nasa.gov/mars-photos) has been returning HTTP 404
`nasa_neo`	read	Near-Earth asteroid close approaches from NASA NeoWs: a feed for up to 7 days (defaults to today, UTC) or a single asteroid by ID. Requires NASA_API_KEY.
`nasa_osdr_files`	read	List the data files (with download links) for a NASA Open Science Data Repository (OSDR) study.
`nasa_power`	read	Daily solar and meteorological data for a point from NASA POWER (Prediction Of Worldwide Energy Resources).
`nasa_ssc_locations`	read	Positions of spacecraft (and the Moon and Sun) over a time range from the NASA Satellite Situation Center (SSCWeb), in geophysical coordinate systems
`nasa_ssc_observatories`	read	Spacecraft and other observatories whose locations the NASA Satellite Situation Center (SSCWeb) can compute, with their data time ranges and resolution.
`nasa_techport`	read	NASA
`nasa_techtransfer`	read	Search NASA
`nasa_tle`	read	Two-line element sets (TLE) for Earth-orbiting satellites from the TLE API in the api.nasa.gov catalog (tle.ivanstanojevic.me; CelesTrak data refreshed daily):
`nasa_trek_layers`	read	Search the map layer catalogs of NASA Mars Trek, Moon Trek and Vesta Trek (trek.nasa.gov): mosaics, colour hillshades and other imagery
`nasa_trek_tile`	read	One WMTS map tile image from NASA Mars Trek, Moon Trek or Vesta Trek for a layer from nasa_trek_layers, addressed by zoom/row/col
`object_name`	read	Name or designation (e.g.
`spk_id`	read	SPK-ID of the object
`start_date`	write	Start of a date range (YYYY-MM-DD)
`test_probe`	read	probe tool

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (5 observation(s))
Network: declared (1 observation(s))
Shell: declared (2 observation(s))
Dependencies: not all pinned
Secrets in source: none-found