Model Finder — Claude Code MCP server: what it does, how to install
Compare AI models against your own tests and find a lower-cost option among those that pass. Use it to assess candidates or prepare model routing.
claude mcp add model-finder -- uvx model-finder-mcpWhat Model Finder does
Model Finder suggests models for a task and budget, runs your examples against selected candidates, then reports pass rate, latency, and billed cost. It can also prepare routing that tries a cheaper model first and moves on when an answer fails quality checks. A separate skill estimates whether a local model fits your GPU.
The package includes four Agent Skills and a local MCP server built for Python 3.9+. The server itself makes no network requests and needs no API keys. Your own provider keys are needed when running evaluations or the generated router. Its output is advisory: it does not deploy anything or change the active model. To add it in Claude Code, run claude mcp add model-finder -- uvx model-finder-mcp.
What it helps with
- test candidate models with your own examples
- compare response cost and latency
- find a lower-cost model that passes your tests
- route failed requests to another model
- check whether a local model fits your GPU
Example prompts for the agent
- Compare several models for this task using my examples, and show their cost and pass rate.
- Find a low-cost model for coding in my IDE and suggest how to test it with my prompts.
- Check whether this local model fits my GPU, including its KV cache.
How to install Model Finder
Platform CLI
claude mcp add model-finder -- uvx model-finder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from model-finder-mcp <command>
Platform CLI
codex mcp add model-finder -- uvx model-finder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from model-finder-mcp <command>
Config file
{
"mcpServers": {
"model-finder": {
"command": "uvx",
"args": [
"model-finder-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from model-finder-mcp <command>
Config file
{
"servers": {
"model-finder": {
"type": "stdio",
"command": "uvx",
"args": [
"model-finder-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from model-finder-mcp <command>
Platform CLI
gemini mcp add model-finder uvx model-finder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from model-finder-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Model Finder
How do I install Model Finder in Claude Code?
Run claude mcp add model-finder -- uvx model-finder-mcp.
What does Model Finder do?
It helps you compare models on your examples, estimate their cost, and prepare routing based on price and test results.
Does Model Finder need API keys?
The local MCP server does not. You need your provider keys to run evaluations and the router, which make requests to the providers you choose.
