Model Radar MCP Server

by srclight Your server? Claim it

local only

Model Radar runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from pypi.

Ping 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.

Installs per day peak 49 · avg 20 · -31% w/w

a month agotoday

103

Installs / week

pypi · model-radar-mcp

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

Nothing serious here today

Today is the operative word: we check Model Radar every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add model-radar -- uvx model-radar-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "model-radar": {
      "command": "uvx",
      "args": [
        "model-radar-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.model-radar]
command = "uvx"
args = ["model-radar-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "model-radar": {
      "command": "uvx",
      "args": [
        "model-radar-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "model-radar": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "model-radar-mcp"
      ]
    }
  }
}

Alternatives to Model Radar

same job, measured the same way

Compute Finance Oracle

by compute-finance

Live AI compute pricing oracle — real-time LLM model prices across providers

401 installs/wk local only

Cheaprouter

by carlosalbertorussell

Routes each LLM completion to the cheapest capable provider across 8 providers (BYOK).

answering

AI API Radar

by dropwatchhq

Live LLM API price + status radar across 11 providers, with public per-model price HISTORY.

4 tools answering

LLM Pricing

by skakumanu

Real-time, drift-verified LLM pricing across 31 providers with cost+quality model routing.

963 installs/wk 32 tools answering

Grandet

by hanzohanzhe

Cheapest API for any model across official, inference and relay providers; find free credits

6 tools answering

Spendline

by spendline

Enforce AI budgets before the model call and track cost per customer across 10 providers.

10 tools answering

ComparEdge LLM Cost

by imkemit-ops

Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.

46 installs/wk local only

Fontpool

by travisvaleri

Search fonts by category, tag and variable axis across three providers, then self-host them.

97 installs/wk local only

Model Radar — questions

Answers built from our own checks of this server.

Why is there no uptime for Model Radar?

Model Radar runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package model-radar-mcp was installed 103 times last week.

How do I connect Model Radar?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls model-radar-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Model Radar?

The pypi package model-radar-mcp was installed 103 times in the last week. Week over week that is -31%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.