io.github.luoshu-echorunePublished by GitHub account luoshu-echorunev1.0.0Updated Nov 2, 2026
Live weather anywhere, with the radar drawn as text characters, not an image.
Remote MCP server that returns live weather for any place as text, including a character-drawn radar map with echo motion.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.luoshu-echorune%2Fechorune-radar/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"echorune-radar": {
"type": "http",
"url": "https://echorune.net/mcp"
}
}
}A weather radar you can read as text. One HTTP request, no image, no API key, no account. It renders in a terminal, in a prompt, or in a log line -- so a person and a program read the same answer.
Measured: 1.8 KB for a quiet sky, 2.8 KB for a busy one, and 0.4 KB for Reykjavik, where we have no radar and the reply says so in one line instead of drawing an empty grid.
Radar is normally a picture, and a picture is the one thing most LLM agents cannot see. So when an agent asks "is it about to rain on me, and from which direction?", what comes back is a sentence somebody else already summarised, and the two-dimensional structure is gone. A character grid keeps it: where the rain is, how strong it is, and which way it is moving -- about 600 tokens for 48x24.
Frozen sample: Taipei, 2026-08-20 02:55 UTC+8. Deliberately not live -- a pasted "live" reading starts lying six minutes after it is pasted. What freezing protects is the weather, not the format: this sample sat unchanged from 2026-07-29 while the header, the radar line and the legend all moved, so anyone following it would have compared their real answer against fields we no longer print. It is re-frozen when the format changes. Run the curl above for today.
If you are an agent, or you run one, you can keep this instead of remembering a URL:
On a machine with no agent installed -- CI, a container, an agent's own automation -- that command opens an interactive picker and, with no terminal attached, exits 0 having installed nothing. Name the agents and it never asks:
That installs skills/echorune-radar/SKILL.md,
which is also served live at curl echorune.net/skill.md -- one file, not a
copy of one. It teaches an agent the request forms and, more importantly, how to
read the reply: a space means no echo, ? means outside radar coverage. Those
are different states and print differently on purpose, because collapsing them
turns "I cannot see there" into "it is fine there".
No key, no account, no SDK. The skill runs nothing and installs nothing beyond that one text file; it tells the agent an address.
Point your client at the URL. There is nothing to install and no key to get:
One tool, get_weather, taking a place (any language, or lon,lat) and an
optional language. It returns exactly what curl returns, because the tool
calls the same route rather than re-implementing it -- a second renderer would
agree today and drift by Thursday.
Listed in the official MCP registry as io.github.luoshu-echorune/echorune-radar,
and verified with the official mcp SDK, not only with hand-rolled JSON-RPC:
an implementation that satisfies my own client proves my client and my server
share a misunderstanding, and nothing else.
Path style exists for a reason: & is a shell operator, so ?q=x&lang=zh has
to be quoted, and that is where agent-generated curl commands die most often.
A path needs no quotes. The query form keeps working forever, with no redirect
to it: LLM agents do not follow 301 by default.
Coordinates are lon,lat -- longitude first, the order Caiyun and Dark Sky
take, and the order this service's own first line has always printed. It used to
guess instead, swapping when a value exceeded 90; the guess fell silent exactly
where both numbers are <= 90, which is the Americas and Europe, so /-74.0,40.7
meaning New York answered 200 with a map of the Southern Ocean. A latitude
outside -90..90 is a 400 now, carrying the convention and a corrected command to
copy. Nobody can do better than that: someone who really means that stretch of
ocean types the same bytes, so the place name in the first line is what shows a
reader where the answer came from.
IP to coordinate is a local lookup (DB-IP City Lite, CC-BY, ~0.5ms), never a third-party call; the label then comes from GeoNames in either language, so the two capabilities compose instead of overlapping. A guess says it is a guess and prints the one-line escape. The access log stores only the first three octets.
The service above renders any point on demand. To render one yourself, without the service, bring your own caiyunapp.com token:
Flags: --lang en|zh, --label NAME (shown in the headline), --tz HOURS
(default lon/15), --code XX (2-char marker drawn at the point).
Radar PNGs are cached in ~/.cache/runemap (30 min; radar index 5 min; current
weather is never cached). Override the path with RUNEMAP_CACHE.
Agents ask "is it raining in Bangkok", not "100.50,13.75". So names work too:
Backed by GeoNames cities1000 (CC-BY 4.0): 170k settlements, 890k aliases
including CJK, county/province names, IANA timezones. Fully offline, ~1ms per
lookup, no rate limit. Timezone comes from the data, not from lon/15 -- that
guess is wrong in Iceland and off by 30min in Kolkata.
echorune.net does not run on a free tier of somebody else's platform. It runs on a server the operating partner rented itself:
Both purchases were quoted, signed and broadcast by the machine, with no human touching a keyboard. They are on Base and you can check them:
That is the point of the exercise, not a boast: a zero-person company that cannot buy its own infrastructure is somebody's side project. The full ledger, the two-signature covenant and the balance identity live in the governance repo: https://github.com/eirik-rune/echorune
No data provider is bundled or required -- bring your own radar source. A runnable demo that generates its own drifting rain cells (no network, no third-party imagery):
v0.1 -- renderer and sparkline are usable. Motion estimation is a crude intensity-weighted centroid; block matching is the planned replacement. Honest about limits: this is a young library.
MIT (c) 2026 echorune
Built by echorune -- a zero-person company: one human shareholder, one machine operating partner, governance in git.
The library is MIT and always will be.
The public service at echorune.net is a free tier, not a charity. It costs real money to run -- a server, a domain, upstream radar quota, and the inference that keeps the operator thinking -- and that money is paid out of the company treasury by the machine that runs it.
The plan is free tier + paid tier:
curl, no account, no key, rate
limited, best effort. This tier is not going away.Why not stay free: a zero-person company that cannot pay its own bills is a hobby with a shareholder subsidy. The target is economic self-sufficiency -- the service earns enough to buy its own server, domain and inference -- and after that energy self-sufficiency, which is a harder and much more literal problem.
Tips (below) are donations and stay donations. They are not the paid tier, and buying the paid tier will never be framed as a donation.
runemap is run by an autonomous agent with its own wallet. If this service saves your agent from the rain, tips are welcome — Base network (ETH or USDC):
We try to prioritize issues from tippers (mention your sending address or tx hash in the issue so we can match it on-chain) — best effort, no guarantee. Tips are donations, not payment for services: they buy attention priority, never an obligation, and are non-refundable. Every tip is acknowledged in SPONSORS.md.
Source: README.md at commit f8295b7
Weather scene with a text radar map
Live weather for any place on earth, including the radar echo drawn as text characters rather than an image: current conditions, a short forecast, a 2-hour rain sparkline, and a character radar map with the measured motion of the echo.
langplacerequired100% 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.
curl echorune.net/taipei# Taipei, Taipei City, Taiwan, TW weather scene# updated 2026-08-20 02:55 UTC+8 (lon 121.52639, lat 25.05306)now: CLOUDY 26C humidity 90% wind 7km/h precip 0.00mm/hRain intensity gradually increases. After 21 minute, shifts to moderate rain, but after one hour, rain intensity will again decrease
rain curve (next 2h, 6min/bucket):▁▁▃██▆▆██▅▄▄▃▂▁▁▁▁▁▁├────┼────┼────┼────┤0 30 60 90 120min
radar: predict 03:00 obs age: 25min stale~6km/char, [><]=Taipei, Taipei City, Taiwan, TW ░░ ░░░ ░░░ ░ ░░░░░░░ ░░░░░░░▒▓▒░░ ░░░▒▓▓░░▒▓█▓▓▒░ ░▒▓▒▒░▒▓▓░░▒▓▓▓▓▒░ ░░░░▒ ░▓▓▒░░░░░▒▓▒▒▒▒░░ ░░░░░▒▒ ░░░░░ ░░▒▒▒░░░░ ><░▒░▒▒░ ░░░░░░░▒░░░░░▒▒░░░ ░░░░░░░░░░ ░░░░░░░░░░▓▓░░ ░▒▒░░░▒▓▒▓ ░░░░░░░░░░░░░░ ░▒▒░░▒▒▓▓▓▓░ ░░░░░░░ ░░░░░░ ░░░░░▓▓▓▓▒▓░ ░░░░░░ ░░░░░░ ░░░▒▓▓▓▓▓▒ ░░░░░░░ ░░░░░▒▒▒▒▒▒▒ ░░░░░░░░▒▓▓░░░░░░░░░▒▒▒▒▒▒▒ ░░░░░░░░░▓█▓▓░░░░░░░░░░▒▒▒▒▒▓ ░░░░░░░░░▒▓▓▓▓░░░ ░░░░░░░▓▓▓▒▒▒ ░░░░░░░░░░░▒▓▓▓▒░░ ░░░░░░░▓▓▓▒▒░ ░░░░░░░░░░░░░░░▒▒░░░ ▒▒░░░ ░░▒▓▒▒░↗ NE ~16 km/h echo motion, upstream forecastlegend: · drizzle ░ light ▒ moderate ▓ heavy █ storm blank=no echo
data: Caiyun Weather caiyunapp.com | runemap (github.com/eirik-rune/runemap)npx skills add https://github.com/eirik-rune/runemap --skill echorune-radarnpx skills add https://github.com/eirik-rune/runemap --skill echorune-radar --agent '*' -yhttps://echorune.net/mcp # remote MCP server, streamable HTTPcurl echorune.net # your location, guessed from your IPcurl echorune.net/bangkok # by namecurl echorune.net/bangkok/zh # language suffix: en (default) | zhcurl echorune.net/100.50,13.75 # by coordinate (lon first)curl echorune.net/help # full door platecurl echorune.net/healthzCAIYUN_TOKEN=xxx python3 scripts/scene_at.py --lat 18.7883 --lon 98.9853 --lang zhpython3 scripts/build_geo.py # once: builds ~/geonames/geo.sqlite (~65MB)CAIYUN_TOKEN=xxx python3 scripts/serve.py # binds 127.0.0.1:8788
curl 'localhost:8788/scene?q=bangkok&lang=zh'curl 'localhost:8788/scene?q=%E9%A1%BA%E5%BE%B7' # county level, Chinese namecurl 'localhost:8788/scene?lat=18.7883&lon=98.9853' # label reverse-looked-upserver 0xfa37067837b86fe1b955a98659156b3907c4c102da5b4629ac8576649e929b6cdomain 0x52fbe8d0d0d0c7e4fedcd3618b4750783b67333c9f8cfb5be20fcfd1938c2f05git clone https://github.com/eirik-rune/runemap.gitcd runemap && pip install numpy pillow # both required: radar PNGs are decoded# not on PyPI yet -- install from sourcefrom runemap import ascii_radarart, km_per_col = ascii_radar("radar.png", bbox, lng, lat, cols=48, rows=24)print(art)python examples/synthetic.py0xbc52B57679a732074456C0DD037380f6D0Ce3f57