Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
ARRL Logbook of The World MCP server. QSO query, QSL status, DXCC credit tracking.
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": {
"lotw": {
"command": "uvx",
"args": [
"lotw-mcp"
]
}
}
}Run this in your terminal
claude mcp add lotw -- uvx lotw-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"lotw": {
"command": "uvx",
"args": [
"lotw-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": {
"lotw": {
"type": "stdio",
"command": "uvx",
"args": [
"lotw-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 8, 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 (0.6.2) 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, Tethered Trust
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.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
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 ARRL Logbook of The World (LoTW) — query confirmations, uploaded QSOs, DXCC credits, and user activity through any MCP-compatible AI assistant.
Part of the qso-graph project. Read-only — uploads require TQSL digital signatures and are out of scope.
uvx lotw-mcp # run it; nothing to install
| Tool | Auth | Description |
|---|---|---|
lotw_confirmations | Yes | Query confirmed QSLs with band/mode/call/date filters |
lotw_qsos | Yes | Query all uploaded QSOs (confirmed and unconfirmed) |
lotw_dxcc_credits | Yes | DXCC award credits from LoTW confirmations |
lotw_download | Yes | Download QSOs as ADIF file |
lotw_user_activity | No | Check if a callsign uses LoTW and when they last uploaded |
get_version_info | No | Service version + upstream LoTW schema version (fleet identity attestation) |
lotw-mcp uses qso-graph-auth personas for credential management:
# Install qso-graph-auth if you haven't
uv tool install qso-graph-auth
qso-graph-auth persona add --name ki7mt --callsign KI7MT --start 2020-01-01 qso-graph-auth provider enable ki7mt lotw qso-graph-auth creds set ki7mt lotw # asks for your username, then your password (hidden)
All three steps are needed: without provider enable, the server reports that the persona has no lotw ref.
Note: The LoTW login is usually your callsign but not always. Pre-Sept 2019 accounts may require lowercase passwords. Avoid special characters in passwords.
Add to claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude\ on Windows):
{
"mcpServers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
Add to .claude/settings.json:
{
"mcpServers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
{
"mcpServers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):
{
"mcpServers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
Add to .vscode/mcp.json in your workspace:
{
"servers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
Add to ~/.gemini/settings.json (global) or .gemini/settings.json (project):
{
"mcpServers": { "lotw": { "command": "uvx", "args": ["lotw-mcp"] } } }
"How many LoTW confirmations did I get this month?"
"Show me all unconfirmed 20m FT8 QSOs uploaded to LoTW in the last 90 days"
"What DXCC credits do I have on 40m CW?"
"Does JA1ABC use LoTW? When did they last upload?"
lotw_user_activity works without any credentials. It uses the public LoTW user activity CSV, cached locally for 7 days.
Set the mock environment variable:
LOTW_MCP_MOCK=1 lotw-mcp
LoTW can be slow (30-60s for large queries). lotw-mcp uses 120s timeouts. Use date filters (since, start_date) to limit result sets.
lotw-mcp --transport streamable-http --port 8004
git clone https://github.com/qso-graph/lotw-mcp.git
cd lotw-mcp uv sync --group dev uv run pytest
GPL-3.0-or-later