io.github.qso-graph/eme-mcp

eme-mcp

Is the io.github.qso-graph/eme-mcp MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-31.

EME prediction for amateur radio: moon windows, path loss and degradation, computed locally

alive probed 2026-11-14 · unchanged since 2026-10-31

5tools

1.1ktokens in Claude Opus 5.5

0.6 %of Claude's 200k window

0.4×the median server

7.6 sto initialize

431 msto list tools

Run it: uvx eme-mcp@0.4.0 (stdio, probed in a container with the network off)
Host: pypi.org
Reports itself as: eme-mcp 0.4.0
Capabilities: logging, prompts, resources, tools
Instructions: 323 characters
Of a 1M window: 0.1 % of a 1M context window
Count: 1.1k tokens in Claude Opus 5.5, exact, measured 2026-10-17. With the Claude Code prefix mcp__…__ on each tool name: 1.2k. The o200k_base estimate is 650. Counted again when the tool definitions change. Method.
Repository: https://github.com/qso-graph/eme-mcp
Registry: active, updated 2026-10-27 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.73×.

Tool	≈ Claude tokens	o200k estimate	Share of this server
eme_path_loss	374	216	33 %
eme_moon_window	372	215	33 %
eme_degradation	183	106	16 %
eme_calendar	125	72	11 %
get_version_info	71	41	6 %

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention graph.

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.