ModelRadar MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODELRADAR_URL | No | Base URL for the ModelRadar catalog | https://modelradar-one.vercel.app |
| OPENROUTER_API_KEY | No | API key for OpenRouter, required only for the modelradar_run tool |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| modelradar_getA | Get full details for one model by id, name, or OpenRouter id. |
| modelradar_latestB | Latest model releases straight from the ModelRadar RSS feed (title, lab, date, link, summary). |
| 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. |
| modelradar_runA | Route + execute: pick the best model for the need (or use |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
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.
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.
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.
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.