Skip to main content
Glama
Sign In
ModelRadar MCP

ModelRadar MCP

by legifx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

ModelRadar MCP

An MCP server that turns the curated ModelRadar catalog into a model router between OpenRouter and your CLI / agent.

  • 🔎 Discover — search the catalog, read the latest releases straight from the RSS feed

  • 🧭 Route — given a need (coding, cheap, open-weights, long-context, multimodal…), get the best OpenRouter-routable model with live pricing and a rationale

  • âš¡ Execute — optionally run the completion through OpenRouter on the chosen model (recommend → route → answer + cost)

Dependency-free. One file, Node ≥ 18, no build step.

Tools

Tool

What it does

modelradar_search

Filter the catalog by type / country / open-weights / min-context / query

modelradar_get

Full details for one model (id, name, or OpenRouter id)

modelradar_latest

Latest releases from the ModelRadar RSS feed

modelradar_recommend

Rank the best routable models for a need (live OpenRouter pricing + why)

modelradar_run

Route and execute: pick a model and run a completion via OpenRouter (needs OPENROUTER_API_KEY)

Related MCP server: Perplexity Ask OpenRouter

Install / run

npx modelradar-mcp           # or: git clone … && node server.mjs

The server speaks MCP over stdio.

Claude Code

claude mcp add modelradar -- npx -y modelradar-mcp
# enable routing+execution:
claude mcp add modelradar -e OPENROUTER_API_KEY=sk-or-... -- npx -y modelradar-mcp

Claude Desktop / generic MCP client (mcpServers)

{
  "mcpServers": {
    "modelradar": {
      "command": "npx",
      "args": ["-y", "modelradar-mcp"],
      "env": { "OPENROUTER_API_KEY": "sk-or-..." }
    }
  }
}

Environment

Var

Required

Default

OPENROUTER_API_KEY

only for modelradar_run

–

MODELRADAR_URL

no

https://modelradar-one.vercel.app

The key is read from the MCP process env only. Never commit it.

Examples

// "cheapest open-weight coding model"
modelradar_recommend { "task": "coding", "open_weights": true, "prefer": "cheap" }
// → Granite 4.1 8B  ibm-granite/granite-4.1-8b  $0.05/MTok in  …

// route + run in one call
modelradar_run { "prompt": "Refactor this function…", "task": "coding", "prefer": "cheap" }
// → routed_to: ibm-granite/granite-4.1-8b · text: … · estimated_cost_usd: 0.0000x

How it works

ModelRadar curates the model catalog (/api/models) and publishes new releases via RSS (/feed.xml). This server reads both, enriches routable models with live OpenRouter pricing, scores them against your request, and (optionally) executes the chosen model through the OpenRouter chat API. ModelRadar is the map; OpenRouter is the road; this MCP is the router in between.

License

MIT

Available Tools

5 tools
modelradar_getA

Get full details for one model by id, name, or OpenRouter id.

Inputs: id_or_name (required).

modelradar_latestB

Latest model releases straight from the ModelRadar RSS feed (title, lab, date, link, summary).

Inputs: limit.

modelradar_recommendB

Recommend the best OpenRouter-routable model(s) for a need. Returns ranked models with live OpenRouter pricing and a rationale — pick one and route your CLI to its openrouter_id.

Inputs: task, limit, query, prefer, +4 more.

modelradar_runA

Route + execute: pick the best model for the need (or use model if given) and run a chat completion through OpenRouter. Returns the answer, the model it routed to, and an estimated cost. Requires OPENROUTER_API_KEY.

Inputs: prompt (required), task, model, query, +8 more.

modelradar_searchA

Search the ModelRadar catalog of AI models. Filter by type/country/open-weights/min context, or free-text query. Set only_routable=true to keep only models usable via OpenRouter.

Inputs: type, limit, query, country, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: search, get details, latest releases, recommend, and run. There is no overlap in their functions, and an agent can easily select the right tool based on the action needed.

    Naming Consistency5/5

    All tools follow the same 'modelradar_' prefix with a simple verb suffix (search, get, latest, recommend, run). This consistent pattern makes the toolset predictable and easy to navigate.

    Tool Count5/5

    The 5 tools are well-scoped for the server's purpose: discovering, inspecting, and running AI models. Each tool earns its place, and the count is neither too thin nor overwhelming.

    Completeness5/5

    The tool surface covers the full workflow: search to find models, get to fetch details, latest to see new releases, recommend to choose a model, and run to execute. There are no obvious dead ends or missing core operations for the stated domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers