space-defense-osint
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@space-defense-osint Find the next ISS pass over Cape Canaveral in the next 24 hours."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-space-defense-osint
A stdio MCP server for public orbital context, geomagnetic conditions and structured airspace envelopes. Built on the official MCP SDK, Skyfield/SGP4 and HTTPX. MIT licensed; Python 3.11+. No API keys required.
Quickstart (30 Seconds)
git clone https://github.com/melgoldstein/mcp-space-defense-osint.git
cd mcp-space-defense-osint
python -m venv .venv
.venv/bin/python -m pip install '.[dev]'
.venv/bin/space-defense-osint --checkWindows equivalents are .venv\Scripts\python.exe and
.venv\Scripts\space-defense-osint.exe. --check performs a local parser check.
Without arguments the CLI serves MCP over stdio; logs go to stderr.
Related MCP server: mcp-celestrak
Claude Desktop configuration
Add this to claude_desktop_config.json, selecting the absolute Python path of the
environment where the package is installed. Restart the host after saving.
{
"mcpServers": {
"space-defense-osint": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["-m", "space_defense_osint.server"]
}
}
}Windows command example: C:\\Users\\you\\tools\\.venv\\Scripts\\python.exe.
Configuration paths: %APPDATA%\Claude\claude_desktop_config.json on Windows and
~/Library/Application Support/Claude/claude_desktop_config.json on macOS.
Cursor accepts the same mcpServers entry in .cursor/mcp.json.
See the SDK host guide
and Cursor documentation.
Tools
Tool | Inputs | Result |
| Catalog ID, location, horizon, minimum elevation | TLE, epoch age, next pass, source and retrieval timestamp |
| None | Latest observed Kp, SWPC alerts, age and cache metadata |
| Notice with ICAO center/radius | GeoJSON bounding envelope, bbox, center and radius |
Pass defaults: Cape Canaveral 28.4158, -80.6048, ISS 25544, 24-hour horizon and
10-degree minimum elevation. The horizon is bounded to 72 hours. Results identify ongoing
passes and truncated search windows. A null pass means no qualifying pass was found.
These are geometric passes, not optical-visibility forecasts.
TLE requests are cached for one hour, NOAA for 60 seconds. Cache hits retain original retrieval timestamps. Requests have a 15-second timeout and two-megabyte body budget. Errors do not silently substitute stale results. NOAA observation age is reported separately; values older than six hours are marked stale. Current object-based and legacy table-based Kp layouts are both supported.
The NOTAM parser supports Q-line coordinates such as 2825N08036W010 with radius
in nautical miles. Dateline crossings produce a MultiPolygon. This is a bounding
envelope, not a legal TFR boundary. Arbitrary polygons and free-form descriptions are
rejected. The tool parses supplied notices; it does not fetch current airspace restrictions.
Python API
from space_defense_osint.server import fetch_celestrak_tle
from space_defense_osint.airspace import analyze_notam_tfr
geometry = analyze_notam_tfr("Q) KZMA/QWALW/IV/M/W/000/999/2825N08036W010")
pass_context = fetch_celestrak_tle(catalog_id=25544)Benchmark comparison
Local medians over 1,000 iterations on Windows x64:
Operation | Median, us | Network included |
Cached feed read | 0.30 | No |
Reparse small JSON fixture | 0.90 | No |
Q-line to GeoJSON | 2.80 | No |
Caching avoids repeated decoding and upstream requests. These operations differ in
semantics; their timings do not estimate live-feed or orbital-prediction latency.
Run python benchmarks/bench_local.py. Results record the platform.
Validation and sources
python -m pytest runs offline geometry, caching, Kp-layout, pass-ordering and real MCP
stdio handshake/tool-call tests. Live NOAA and CelesTrak checks also passed during development.
Live availability varies; consumers should inspect TLE epoch age before using predictions.
Legacy TLE catalog identifiers above 99999 require an OMM interface and are not supported.
Available Tools
3 toolsanalyze_notam_tfrC
Convert an ICAO Q-line center/radius to a GeoJSON bounding envelope.
Inputs: notice (required). Returns: object
fetch_celestrak_tleB
Fetch one TLE and predict the next topocentric pass; returns source and epoch age.
Inputs: latitude, longitude, catalog_id, horizon_hours, +1 more. Returns: object
query_noaa_swpc_kpA
Fetch observed planetary Kp and current SWPC alerts with retrieval timestamps.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a clearly different data source and task: space-weather Kp/alerts, NOTAM TFR geometry conversion, and satellite TLE/pass prediction. There is no meaningful overlap that would cause misselection.
All names use snake_case and follow a verb_source_or_data pattern: query_noaa_swpc_kp, analyze_notam_tfr, fetch_celestrak_tle. The differing verbs reflect genuinely different operations rather than inconsistent conventions.
Three tools is a reasonable minimal set, and each has a distinct purpose. For a broad 'space-defense-osint' server it still feels somewhat thin, but the count is not excessive or clearly mismatched.
The surface provides only narrow primitives: current Kp/alerts, a NOTAM Q-line conversion, and a single TLE pass prediction. It lacks obvious OSINT operations such as fetching NOTAM/TFR records, querying multiple satellites, historical/forecast space weather, or cross-source correlation.
Related MCP Connectors
Unofficial N2YO MCP — wraps the N2YO Satellite Tracking REST API (n2yo.com)
Unofficial NASA MCP — wraps NASA Open APIs (api.nasa.gov)
MCP server for aerospace calculations: orbital mechanics, ephemeris, DSN operations, ...
CelesTrak MCP — satellite orbital elements (TLE / GP data) for any tracked object.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceMCP server that wraps the NASA Space-Track API to provide tools for TLE lookup, conjunction query, and satellite catalog search.-
- AlicenseNot gradedqualityCmaintenanceProvides satellite orbital elements (TLE / GP data) for any tracked object via MCP.98 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables discovery, analysis, and explanation of open satellite data through MCP, with support for STAC catalogs and NASA GIBS.1MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that equips LLM clients with authoritative astrodynamics tools including TLE/SGP4 propagation, Lambert solving, ground-station access, time-scale and coordinate-frame conversions, and more.83 PyPI2MIT