# Exoplanet Archive [Health: Active]

**Category:** 🚀 Aerospace & Astrodynamics  
**Repository:** https://github.com/pipeworx-io/mcp-exoplanet-archive  
**GitHub Stars:** 0  
**npm Downloads (last month):** 471  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/exoplanet-archive

## Description
NASA Exoplanet Archive — ~5600 confirmed exoplanets + candidates

## Tools
Capabilities this server exposes over MCP:

- **tap** — ADQL TAP query. For "how many confirmed exoplanets" or any per-planet count, query `pscomppars` (one row per confirmed planet) or COUNT(DISTINCT pl_name) -- never a bare COUNT(*) FROM ps, which counts published parameter SOLUTIONS (several per planet, currently ~40k rows for ~6.5k planets) and silently over-counts by 6x. Prefer the dedicated confirmed_planet_count tool for planet-count questions.
- **planets** — Per-solution search against the `ps` (Planetary Systems) table -- one row per published parameter SOLUTION, with several solutions per confirmed planet. Good for comparing how a planet's measured parameters changed across papers; NOT a planet count or a clean per-planet list (its row count is parameter solutions, not planets). For planet counts or one-row-per-planet listings use `composite` or `confirmed_planet_count` instead.
- **composite** — Composite planet parameter table `pscomppars` -- one row per confirmed planet. Use this (or `confirmed_planet_count`) for "how many confirmed exoplanets" questions and for any per-planet listing; do not use `ps`/`tap` for those, since `ps` has several rows per planet.
- **confirmed_planet_count** — Count of confirmed exoplanets -- from the composite parameter table `pscomppars` (one row per planet), not the per-solution `ps` table. Use this for "how many confirmed exoplanets" questions. Optional filter narrows the count, e.g. "disc_year = 2023" for planets discovered that year. Returns the unit and the date of the live query.
- **kepler_candidates** — Kepler Object of Interest (KOI) candidate table -- unconfirmed candidates, not confirmed planets. Do not use this table's row count to answer a confirmed-planet-count question.
- **microlensing** — Microlensing event table -- detection events, not a planet count.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "exoplanet-archive": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-exoplanet-archive"]
  }
}
```

## Documentation & README

# @pipeworx/exoplanet-archive

NASA [Exoplanet Archive](https://exoplanetarchive.ipac.caltech.edu) MCP — ~6,451 confirmed exoplanets + candidates + light curves. Keyless TAP service.

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1866+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

## A row-grain trap: `ps` vs `pscomppars`

The archive publishes two planet tables with different row grains, and mixing
them up silently over-counts planets by ~6x:

- **`ps`** (Planetary Systems) — one row per published parameter **solution**.
  A planet re-measured across several papers gets several rows, so
  `COUNT(*) FROM ps` counts solutions, not planets (40,350 rows for 6,451
  confirmed planets, 2026-10-16).
- **`pscomppars`** (Planetary Systems Composite Parameters) — one row per
  confirmed **planet**. This is the right table for "how many confirmed
  exoplanets" and for any per-planet listing.

Use `confirmed_planet_count` or `composite` for planet counts/listings. If you
query `ps` directly (via `planets` or `tap`), filter `default_flag = 1` or
count `DISTINCT pl_name` to get one row per planet; every response from this
pack names its row unit so this can't be missed silently.

## Tools

- `tap(query, format?)` — ADQL TAP query against the archive (default table: `ps`). A raw `COUNT(*) FROM ps` without `default_flag`/`DISTINCT` comes back with a `warning` field, not a bare number.
- `planets(query?, limit?)` — per-solution search against the `ps` table; every response carries a `unit` field naming the row grain
- `composite(query?, limit?)` — query the composite planet parameter table `pscomppars` (one row per confirmed planet)
- `confirmed_planet_count(query?)` — count of confirmed exoplanets from `pscomppars`, with its unit and the date of the live query; optional WHERE-clause filter (e.g. `disc_year = 2023`)
- `kepler_candidates(query?, limit?)` — Kepler Object of Interest (KOI) table (unconfirmed candidates)
- `microlensing(query?, limit?)` — microlensing event table

## Data source

NASA Exoplanet Archive, TAP service.

## Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

```json
{
  "mcpServers": {
    "exoplanet-archive": {
      "url": "https://gateway.pipeworx.io/exoplanet-archive/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/exoplanet-archive/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:

```json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}
```

Both URLs reach the same gateway and the same 1866+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.

## No MCP client? Call it over HTTP

```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/exoplanet_archive_tap \
  -H 'Content-Type: application/json' \
  -d '{"query":"SELECT TOP 5 pl_name, sy_dist FROM ps"}'
```

No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/exoplanet_archive_tap`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.

## Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no
gateway round-trip:

```json
{
  "mcpServers": {
    "exoplanet-archive": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-exoplanet-archive"]
    }
  }
}
```

Or run it directly to confirm it starts:

```bash
npx -y @pipeworx/mcp-exoplanet-archive
```

It speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`
for **only** this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.

## Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:

```
ask_pipeworx({ question: "your question about Exoplanet Archive data" })
```

The gateway picks the right tool and fills the arguments automatically.

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT