Connects to ARRL's Logbook of The World to query QSO confirmations, DXCC credits, and uploaded contacts through six tools. You can filter QSLs by band, mode, callsign, and date, check DXCC award progress, or look up whether a callsign uses LoTW and when they last uploaded. Requires qso-graph-auth personas for credential management, though the user activity lookup works without authentication. Responses can be slow since LoTW itself takes 30 to 60 seconds on large queries, so you'll want to use date filters. Read-only by design since uploads need TQSL digital signatures. Useful if you're working with contest logs, tracking award progress, or building tools around amateur radio contact verification.
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.
pip install lotw-mcp
| 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:
pip install qso-graph-auth
qso-auth persona create ki7mt --callsign KI7MT
qso-auth persona provider ki7mt lotw --username KI7MT
qso-auth persona secret ki7mt lotw
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": "lotw-mcp"
}
}
}
Add to .claude/settings.json:
{
"mcpServers": {
"lotw": {
"command": "lotw-mcp"
}
}
}
{
"mcpServers": {
"lotw": {
"command": "lotw-mcp"
}
}
}
Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"lotw": {
"command": "lotw-mcp"
}
}
}
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"lotw": {
"command": "lotw-mcp"
}
}
}
Add to ~/.gemini/settings.json (global) or .gemini/settings.json (project):
{
"mcpServers": {
"lotw": {
"command": "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
pip install -e .
GPL-3.0-or-later