Local BYOK MCP for AI model shortlisting using OpenRouter + Artificial Analysis.
registry version 0.2.4
npm
npx -y @agentic.artists/modelshortlistnpm
npx -y @agentic.artists/modelshortlist@0.2.4
Pick your client — the config below is generated for this server (local stdio). Copy respects the “Pin version” switch above.
claude_desktop_config.json
{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist@0.2.4"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add --env ARTIFICIAL_ANALYSIS_API_KEY=<YOUR_ARTIFICIAL_ANALYSIS_API_KEY> --env OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY> modelshortlist -- npx -y @agentic.artists/modelshortlist
claude mcp add --env ARTIFICIAL_ANALYSIS_API_KEY=<YOUR_ARTIFICIAL_ANALYSIS_API_KEY> --env OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY> modelshortlist -- npx -y @agentic.artists/modelshortlist@0.2.4
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist@0.2.4"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}{
"servers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist@0.2.4"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}{
"mcpServers": {
"modelshortlist": {
"command": "npx",
"args": [
"-y",
"@agentic.artists/modelshortlist@0.2.4"
],
"env": {
"ARTIFICIAL_ANALYSIS_API_KEY": "<YOUR_ARTIFICIAL_ANALYSIS_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>"
}
}
}
}Format verified against the official Windsurf docs ↗.
Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.
ARTIFICIAL_ANALYSIS_API_KEY required secret — Artificial Analysis API key used to fetch benchmark and model-performance data.OPENROUTER_API_KEY required secret — OpenRouter API key used to fetch model catalog and optional ZDR endpoint data.⭐ 1 stars · 最近更新于 26 天前 · MIT license
ModelShortlist Stop guessing which AI model to use. ModelShortlist is a local, bring your own key MCP server that gives your AI assistant model selection evidence from the full OpenRouter model catalog plus Artificial Analysis benchmarks . It refreshes upstream evidence on demand/cache expiry and ex…
Summary from the project README — github.com/AgenticArtists/ModelShortlist
Distributed as npm, listed under Developer Tools. Review our MCP security guide before granting access to real data.
ModelShortlist Stop guessing which AI model to use. ModelShortlist is a local, bring your own key MCP server that gives your AI assistant model selection evidence from the full OpenRouter model catalog plus Artificial Analysis benchmarks . It refreshes upstream evidence on demand/cache expiry and ex
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/AgenticArtists/ModelShortlist. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/modelshortlist/)
HTML
<a href="https://mcpnav.net/server/modelshortlist/"><img src="https://mcpnav.net/badge/modelshortlist.svg" alt="Listed on MCPNav" height="20"></a>