Exoplanet DB

Published Catalog Snapshots

Exoplanet DB maintains an immutable ledger of every ingestion run and catalog publication. Every release is linked to upstream commit SHAs and validation hashes.

AI Agent & Model Context Protocol (MCP) Interface

Exoplanet DB is architected specifically for AI agents, pairing a read-only REST API with an MCP server. Agents can explore targets, query signals with strict epistemic dispositions, examine candidate dossiers, and check novelty against published records.

Available MCP Tools

• lookup_target(name_or_id) — Resolves target names, TIC IDs, Gaia DR3 IDs, and host star stellar parameters.
• search_signals(disposition, min_period, max_period, min_depth, limit) — Structured query over catalog signals.
• get_dossier(signal_id) — Comprehensive candidate dossier including transit ephemeris fits, timing consistency, localisation status, and scientific limits.
• check_novelty(ra_deg, dec_deg, period_d, epoch_bjd, depth_ppm) — Returns evidentiary snapshots with timestamps, commit SHAs, near-matches, and unindexed sources. Strictly avoids subjective booleans.

MCP Server Configuration

Connects external AI agents directly to the public read-only HTTPS REST API. No database credentials or internal cluster access required.

{
  "mcpServers": {
    "exoplanet-db": {
      "command": "python",
      "args": ["-m", "exoplanet_db.mcp.server"],
      "env": {
        "EXOPLANET_API_URL": "https://exoplanets.brahle.com"
      }
    }
  }
}