Back to code-only MCP servers

model-radar

active

MCP server that pings 130+ free coding LLM models across 17 providers in real-time, ranks by latency, and helps AI agents pick the fastest available model.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/srclight/model-radar
Package
pypi: model-radar-mcp
Run (stdio)
uvx model-radar-mcp
The usual command for this package registry; check the repository README for required settings.
License
MIT
Last update
2026-08-31
GitHub stars
★ 0

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.