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. 130 installs a week from pypi.

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

Installs per day peak 357 · avg 40 · -24% w/w

a month agotoday

130

Installs / week

pypi · model-radar-mcp

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

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

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

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

250 installs/wk local only

AI API Radar

by dropwatchhq

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

4 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.

30 installs/wk local only

Promptster

by promptster-dev

Test and compare prompts across any AI provider. Bring your own keys.

answering

Data Cleaner Agent

by wesseltl

Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.

119 installs/wk local only

Car Repair Cost Estimator

by carrepaircostestimator

Car repair cost estimates by make, model and repair type. 31 cost guides, VIN decode. Free.

7 tools answering

Video Generation Cost Estimator

by 702exec

Video generation cost estimates across providers, with provenance, freshness, and confidence.

3 tools answering

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 130 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 with the file path 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 130 times in the last week. Week over week that is -24%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.