LLM Radar
Offers data on Google's Gemini models, including model IDs, pricing, context windows, capabilities, and release status, allowing AI assistants to search and compare models like Gemini 1.5 Pro and Flash.
Provides current information about OpenAI's AI models, including model IDs, pricing, context windows, capabilities, and status, enabling AI assistants to query and compare models like GPT-4 and GPT-3.5.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LLM Radar compare GPT-4o and Claude Sonnet"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
⚠️ Project Retired (2026-05-01)
LLM Radar is no longer maintained. The daily data pipeline has been disabled and the repository is archived.
The live dashboard and MCP server may stop working as upstream APIs change. The model data in
data/reflects the last update before retirement.Code remains here for reference only. Forks are welcome.
LLM Radar
Real-time AI Model Intelligence via MCP
Skip the search. Your AI already has current model info.
Live Dashboard · Model Reference · MCP Setup · Contributing
What is LLM Radar?
LLM Radar is an MCP server that gives your AI assistant current information about AI models from OpenAI, Anthropic, and Google.
The problem: AI assistants have training cutoffs. Ask about models and you get outdated recommendations, deprecated APIs, or hallucinated pricing.
The solution: Connect LLM Radar and your AI already knows what's available today:
Fetching fresh data from provider APIs daily
Enriching it with Claude for better descriptions
Exposing it via MCP for any compatible client
Related MCP server: tokencost-mcp-server
MCP Server Setup
Install via pip
# Install
pip install llm-radar-mcp
# Or run directly
pip install llm-radar-mcp && llm-radar-mcpClaude Desktop config (local stdio):
{
"mcpServers": {
"llm-radar": {
"command": "llm-radar-mcp"
}
}
}Option 3: Docker
docker run -p 8000:8000 ghcr.io/ajentsor/llm-radar:latestThen connect to http://localhost:8000/sse
Available MCP Tools
Once connected, you can use these tools:
Tool | Description |
| Search/filter models by provider, type, or modality support |
| Side-by-side comparison of specific models |
| Get detailed info about a specific model by API ID |
| List all available model IDs for a provider |
Example Queries
"What models support vision input?"
→ Uses query_models with input_modality="image"
"Compare GPT-4o, Claude Sonnet, and Gemini 2.5 Pro"
→ Uses compare_models with those model IDs
"List all OpenAI model IDs"
→ Uses list_model_ids with provider="openai"Available Resources
The MCP server also exposes resources you can read directly:
Resource URI | Description |
| Complete JSON data |
| OpenAI models only |
| Anthropic models only |
| Google models only |
| Curated recommendations |
How It Works
┌─────────────────────────────────────────────────────────────────┐
│ Daily GitHub Action (8am UTC) │
├─────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ OpenAI │ │Anthropic │ │ Google │ ← Fetch APIs │
│ │ API │ │ API │ │ API │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
│ │ │ │ │
│ └──────────────┼──────────────┘ │
│ ▼ │
│ ┌──────────────┐ │
│ │ Claude │ ← Enrich & Format │
│ │ (Sonnet) │ │
│ └──────┬───────┘ │
│ │ │
│ ┌─────────────┼─────────────┐ │
│ ▼ ▼ ▼ │
│ ┌─────────┐ ┌──────────┐ ┌───────────┐ │
│ │models. │ │ MCP │ │ GitHub │ ← Deploy │
│ │ json │ │ Server │ │ Pages │ │
│ └─────────┘ └──────────┘ └───────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘Data Format
Each model includes:
Field | Description |
| API model identifier |
| Human-friendly name |
| openai, anthropic, or google |
| What the model is best for |
| Max input tokens |
| Input/output cost per 1M tokens |
| vision, function_calling, reasoning, etc. |
| active, preview, or deprecated |
| Release date |
| Use case suggestions |
Local Development
# Clone
git clone https://github.com/ajentsor/llm-radar.git
cd llm-radar
# Install
python3 -m venv venv
source venv/bin/activate
pip install -e ".[dev]"
# Run MCP server (stdio mode)
llm-radar-mcp
# Run MCP server (HTTP mode for testing)
llm-radar-mcp --http --port 8000
# Fetch fresh data (requires API keys)
cp .env.example .env
# Edit .env with your API keys
python3 -m llm_radar.fetch_models
python3 -m llm_radar.aggregate_with_claudeProject Structure
llm-radar/
├── src/llm_radar/ # Main package
│ ├── __init__.py
│ ├── mcp_server.py # MCP server implementation
│ ├── fetch_models.py # API fetchers
│ └── aggregate_with_claude.py # Claude enrichment
├── data/
│ ├── models.json # Structured model data
│ ├── MODELS.md # Human-readable reference
│ └── raw/ # Raw API responses
├── docs/ # Landing page (Cloudflare)
├── Dockerfile # Container build
├── docker-compose.yml # Local container setup
├── pyproject.toml # Python package config
└── .github/workflows/
└── update-models.yml # Daily cron jobConfiguration
To run the data fetcher yourself:
# .env file
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=AI...For GitHub Actions, add these as repository secrets.
Self-Hosting
Docker Compose
version: '3.8'
services:
llm-radar:
image: ghcr.io/ajentsor/llm-radar:latest
ports:
- "8000:8000"
restart: unless-stoppedCloudflare Workers / Fly.io / Railway
The MCP server supports HTTP/SSE transport, making it deployable to any platform that supports long-running HTTP connections.
Contributing
See CONTRIBUTING.md for guidelines.
Key areas for contribution:
Additional providers (Cohere, Mistral, etc.)
More MCP tools
Better data enrichment prompts
Documentation improvements
License
MIT License - see LICENSE
Built for developers who want accurate AI model info
Available Tools
4 toolscompare_modelsA
Compare specific models side-by-side. Provide model IDs to get a detailed comparison.
Inputs: model_ids (required).
get_modelA
Get detailed information about a specific model by its API ID.
Inputs: model_id (required).
list_model_idsB
List all available model IDs for a provider. Useful for finding exact API identifiers.
Inputs: provider.
query_modelsB
Search and filter AI models available via API. Filter by provider, type, or modality support.
Inputs: provider, model_type, supports_images, supports_audio, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: comparing models, fetching details, listing IDs, and searching. No overlap.
All tools follow a consistent verb_noun snake_case pattern (compare_models, get_model, list_model_ids, query_models).
Four tools cover the essential operations for exploring AI models without being excessive or insufficient.
The set covers listing, searching, details, and comparison; query_models allows broad searches, so no critical gaps are apparent.
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that retrieves and provides AI model information from OpenAI, Anthropic, and Google through a unified interface.384 npmMIT
- AlicenseAqualityDmaintenanceAn MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers.624 npm2MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables agents to dynamically switch between multiple AI models (OpenAI, Anthropic, Google, etc.) with unified protocol-driven configuration and capability discovery.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server that helps AI assistants automatically find, filter, and rank the best AI models for a specific task using the OpenRouter API.1MIT