Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
NetLogger MCP server. Nets on the air, live check-ins and who's up, past nets.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"netlogger": {
"command": "uvx",
"args": [
"netlogger-mcp"
]
}
}
}Run this in your terminal
claude mcp add netlogger -- uvx netlogger-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"netlogger": {
"command": "uvx",
"args": [
"netlogger-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"netlogger": {
"type": "stdio",
"command": "uvx",
"args": [
"netlogger-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account qso-graph, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.3.1) reached the registry 9 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
MCP server for NetLogger: nets on the air now, live check-in lists and who's up, and past nets and their check-ins, through any MCP-compatible AI assistant.
Data from NetLogger's public XML Data Service (API 1.3). Part of the qso-graph project. No API key needed. Your callsign is asked for once (see below).
uvx netlogger-mcp # run it; nothing to install
| Tool | Description | Key Parameters |
|---|---|---|
netlogger_active_nets | Nets on the air now: frequency, band, mode, net control, logger, monitoring count | name_like |
netlogger_checkins | A live net's check-in list, plus the pointer (the station being worked now) | server_name, net_name |
netlogger_past_nets | Closed nets over the last N days, with the net IDs past check-ins need | interval_days, name_like |
netlogger_past_checkins | A closed net's check-in list | server_name, net_name, net_id |
netlogger_set_callsign | Save your callsign (asked once, on first use) | callsign |
get_version_info | Service version + upstream spec version (fleet identity attestation) | — |
NetLogger is the logging program many amateur-radio nets use: net control or a logger keeps the check-in list, and anyone can follow the net live. Its server publishes active nets, check-in lists and past nets through a public API.
Every request tells NetLogger which station is asking, so it can tell one user from another:
netlogger-mcp/<version> (KI7MT; +https://github.com/qso-graph/netlogger-mcp)
The version is the installed one — it is read from the package, not written here.
On first use the assistant asks for your callsign and saves it. You're asked once. To set it yourself, use NETLOGGER_MCP_CALLSIGN=KI7MT.
It's saved in settings.json, in ~/.config/netlogger-mcp/ (Linux), ~/Library/Application Support/netlogger-mcp/ (macOS) or %APPDATA%\netlogger-mcp\ (Windows).
NetLogger is a donation-funded service on one server, and it limits how often each call may be made. We keep to those limits:
| Measure | Detail |
|---|---|
| NetLogger's call limits | GetActiveNets 1/min, GetCheckins 3/min, GetPastNets 1/min, GetPastNetCheckins 10/min. Checked before a request is sent, never after. |
| One budget per user | Every copy you run (Claude Desktop, Claude Code, a script) shares one budget, through a locked file beside settings.json. |
| Shared answers | Every copy also shares the answers it fetched, so a copy that has hit the limit gets another copy's recent answer, with its age, instead of an error. |
| Response caching | Active nets 60 s, check-ins 20 s, past nets 60 s, past check-ins 1 hour. Filtering by name costs no extra calls. |
| How old an answer is | Every answer has as_of_utc (when it was given) and age_seconds (how old the data is), so it was fetched at as_of_utc minus age_seconds. |
| Stale answers over errors | When a limit is reached, the last answer comes back with its age rather than a new request. |
| 429 back-off | A "too many requests" on any call stops all calls for at least a minute, longer if NetLogger asks. |
| Past-net windows | More than 7 days of past nets needs a name filter, NetLogger's rule to protect its server. |
| Request timeout | 15-second timeout. |
| User-Agent header | Every request names this project and your callsign, so NetLogger's operators can see who is asking. |
NetLogger's band and frequency are whatever the logger typed ("40M", "75M", "DMR", "7033", "3918 KHz", "147.030 91.5", "TG 3141"). They're returned as typed, and beside them, only when the text can be read reliably: frequency_mhz, band_adif (the ADIF band, from ADIF 3.1.7's Band enumeration), tone_hz and talkgroup. A frequency outside the amateur bands (e.g. GMRS) gets no band_adif.
NetLogger's check-in data includes street addresses and ZIP codes, and past nets include the IP address of whoever opened them. None of these are ever returned.
netlogger-mcp works with any MCP-compatible client. Add the server config and restart. The tools appear automatically.
Add to claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude\ on Windows):
{
"mcpServers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
Add to .claude/settings.json:
{
"mcpServers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
{
"mcpServers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):
{
"mcpServers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
Add to .vscode/mcp.json in your workspace:
{
"servers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
Add to ~/.gemini/settings.json (global) or .gemini/settings.json (project):
{
"mcpServers": { "netlogger": { "command": "uvx", "args": ["netlogger-mcp"] } } }
"What nets are on the air right now?"
"Are any 80m nets running?"
"Who's checked into the county ARES net, and who's up now?"
"Which nets ran in the last three days?"
"Show me the check-ins from last night's net."
The same code works without an AI, with the same limits and cache. A library can't ask for your callsign, so you pass it in:
from netlogger_mcp.netlogger import NetLoggerSource
nl = NetLoggerSource(callsign="KI7MT") for net in nl.active_nets()["nets"]: live = nl.checkins(net["server"], net["name"]) print(net["name"], "up now:", live["pointer_callsign"])
Apps can also name themselves, using ADIF's PROGRAMID and PROGRAMVERSION: NetLoggerSource(callsign="KI7MT", program_id="MyLogger", program_version="1.0").
NETLOGGER_MCP_MOCK=1 netlogger-mcp
netlogger-mcp --transport streamable-http --port 8014
git clone https://github.com/qso-graph/netlogger-mcp.git
cd netlogger-mcp uv sync --group dev uv run pytest
GPL-3.0-or-later. adif_band.json is the ADIF 3.1.7 Band enumeration, the work of the ADIF Developers Group (adif.org.uk), included unchanged.