Rival

Provides access to rival.tips model benchmarks, pricing, and capability data via an MCP-compatible server.

javascript

0

GitHub Stars

javascript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nuance-dev-rival-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "rival-mcp"
      ]
    }
  }
}

You can query rival.tips model benchmarks, pricing, capabilities, and side-by-side comparisons directly from your editor by running this MCP server. It speaks through standard input and output, letting AI assistants fetch up-to-date model data without leaving your development environment.

How to use

You use this MCP server by connecting it to compatible AI coding assistants that support MCP. Start the server locally and then point your editor’s MCP client to the local process. The server exposes a set of tools you can call to list models, get model details, compare models, and search models. When you invoke a tool, the server fetches data from rival.tips and returns structured results for you to display inside your editor.

How to install

Prerequisites: you need Node.js and npm (or npx) installed on your system.

Install and run the MCP server locally using the quick start command.

Configuration for editors and clients

{
  "mcpServers": {
    "rival": {
      "command": "npx",
      "args": ["-y", "rival-mcp"]
    }
  }
}

Additional client setups

{
  "mcpServers": {
    "rival": {
      "command": "npx",
      "args": ["-y", "rival-mcp"]
    }
  }
}

Available tools and how to use them

The MCP server provides these tools to interact with rival.mcp data:

Data sources and content

All data comes from rival.tips, a public platform with model benchmarks, pricing, capabilities, and side-by-side comparisons.

License

MIT license.

Available tools

list-models

List all AI models with optional filters for provider, category, capability, and a free-text query.

get-model

Retrieve detailed information about a specific model, including benchmarks, pricing, and capabilities.

compare-models

Compare 2-3 models side by side across benchmarks, pricing, capabilities, and shared challenges.

search-models

Search for models by name, description, or capability when you don’t know the exact model ID.