Qsp Mcp
About
Named after the Q-signal QSP ("Will you relay?"), qsp-mcp relays tool calls between a local LLM and MCP servers. Any model with function calling capability gains access to the full qso-graph tool ecosystem — 71+ tools across 12 servers — from local weights, not from cloud.
Details
- Author
- qso-graph
- Downloads
- 361
- Categories
- Other, AI, Developer Tools
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Qsp McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
{
"mcpServers": {
"qsp-mcp": {
"command": "qsp-mcp",
"args": [
"--config",
"~/.config/qsp-mcp/config.json"
]
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"qsp mcp": {
"qsp-mcp": {
"command": "qsp-mcp",
"args": [
"--config",
"~/.config/qsp-mcp/config.json"
]
}
}
}
}McpServers
{
"qsp-mcp": {
"command": "qsp-mcp",
"args": [
"--config",
"~/.config/qsp-mcp/config.json"
]
}
}Overview
qsp-mcp is the tool relay for the qso-graph ecosystem. It bridges any OpenAI-compatible local LLM to MCP servers:
- Sovereign Inference — Use llama.cpp, Ollama, vLLM, or SGLang with full MCP tool access
- Zero Cloud — All inference stays on your hardware, credentials stay in OS keyring
- 71+ Tools — Access all 12 qso-graph servers (propagation, logging, POTA, SOTA, WSPR, solar, and more)
- Profiles — Named server subsets (contest, propagation, full) to focus tool selection
Install: pip install qsp-mcp
Part of the https://qso-graph.io project — a suite of MCP servers for amateur radio.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
