get_version_info
Get Version Info
Get eme-mcp's version and the ephemeris series it computes from.
Takes no parameters.
Eme Mcp
io.github.qso-graphPublished by GitHub account qso-graphv0.4.0Updated Nov 3, 2026
EME prediction for amateur radio: moon windows, path loss and degradation, computed locally
Overview
AI-generated overview
Local MCP server for amateur-radio EME (moonbounce) planning: moon windows from a grid square, path loss and degradation, computed offline.
- What you can do
- Compute moon azimuth, elevation and range from a grid square over time, and the mutual window when both ends of a schedule can see the moon
- Estimate one-way, round-trip and echo path loss on 2m, 70cm, 23cm or any frequency
- Report how much worse than perigee the current or a given moment is, with the moon's declination
- List the least degraded days ahead
- Report the server version and the ephemeris series it computes from
- When to use it
- For radio amateurs planning moonbounce contacts: checking whether the moon is up from one or both stations, budgeting a station with echo path loss, and picking the least degraded days for a schedule.
- Requirements
- Runs as a local stdio process, launched for example with uvx from the PyPI package eme-mcp. No network access, authentication, API keys or environment variables are needed; positions are computed locally from an ephemeris series.
Before you install
Degradation and calendar results cover only the distance term; sky noise from the galactic background is not included and the server says so in every answer. Elevations are geometric, without atmospheric refraction, so objects near the horizon are off by about half a degree. Echo and round-trip path loss are different figures and are often confused.
Installation
In SourceWeft
- Open Eme Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
eme-mcp
MCP server for EME — Earth-Moon-Earth, moonbounce. When the moon is up from your grid, when it is up from both ends of a schedule at once, what the path costs on 2m, 70cm and 23cm, and which days ahead are least degraded.
Part of the qso-graph project. No network, no authentication.
Why it needs nothing from the network
The moon's position is computed here, from the abridged ELP-2000/82 series as Meeus tabulates it (Astronomical Algorithms, chapter 47). That is around 250 lines of standard library and a coefficient table. It is also what WSJT-X does, and the norm for EME software.
That matters for more than tidiness. Moonrise and moonset are different for every grid square, so a service-backed answer means a request per location per query — and a planning tool that stalls, rate-limits, or goes dark when a remote service does.
JPL Horizons is still here — as the test oracle. Recorded Horizons responses are fixtures, so every CI run checks these numbers against NASA's rather than against themselves. Measured against Horizons for a Boise grid:
Thirty arcseconds, against a 432 MHz array that is degrees wide.
Install
Tools
What this does not yet do
Sky noise is not included. The full degradation figure an EME operator plans with
combines the distance term with the galactic background behind the moon, from the Haslam
408 MHz all-sky map. That map is not yet carried and pinned, so eme_degradation and
eme_calendar report the distance term and say so in every answer rather than
returning a number that looks complete and is not. Tracked in
qso-graph-devel#52.
Elevations are geometric: no atmospheric refraction, which lifts an object near the horizon by about half a degree.
The two path-loss figures
They answer different questions and are often confused, so both are returned:
echo_dbis the one to budget a station with — the radar equation, accounting for the moon reflecting about 6.5% of what reaches it. Near 252 dB on 2m, 262 on 70cm and 271 on 23cm at mean distance, which are the numbers EME operators know.round_trip_dbis twice the free-space loss. It ignores the moon entirely.
Licence
GPL-3.0-or-later. See LICENSE.
The algorithms are from Jean Meeus, Astronomical Algorithms (2nd edition, Willmann-Bell, 1998), chapters 7, 11, 12, 22, 40 and 47 — cited in the source where each is used. The implementation is ours; the mathematics is his and is not claimed.
Source: README.md at commit 443089d
Tools
5eme_moon_window
Eme Moon Window
Where the moon is from a grid square, and when both ends of a schedule can see it.
Parameters
hourslocatorrequiredstep_minutesother_locatoreme_path_loss
Eme Path Loss
What the path to the moon and back costs, now or at a given time.
Parameters
bandwhenlocatorfrequency_mhzeme_degradation
Eme Degradation
How much worse than the best case the moon is, now or at a given time.
Parameters
whenlocatoreme_calendar
Eme Calendar
The least degraded days ahead — when the moon is nearest.
Parameters
daysVersion history
6- v0.4.0LatestOct 29, 2026
- v0.3.0Oct 26, 2026
- v0.2.3Oct 26, 2026
- v0.2.1Oct 26, 2026
- v0.2.0Oct 25, 2026
- v0.1.1Oct 11, 2026
Score
90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listedRequired15 pts
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts