INDIVIDUAL MCP TOOL

recommend_model

Recommend the best AI model for a specific task based on ModelPicker's benchmark data.

modelpicker.netnone authenticationAvailability not checked

Input schema

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.modelpicker-net]
url = "https://mcp.modelpicker.net/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "modelpicker-net": {
      "type": "http",
      "url": "https://mcp.modelpicker.net/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: modelpicker-net
Remote MCP URL: https://mcp.modelpicker.net/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "modelpicker-net": {
      "url": "https://mcp.modelpicker.net/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "modelpicker-net": {
      "type": "http",
      "url": "https://mcp.modelpicker.net/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "modelpicker-net",
  "transport": "streamable-http",
  "url": "https://mcp.modelpicker.net/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

list_tasks — List all task categories that ModelPicker scores models on, with their benchmark mappings.
list_benchmarks — List all benchmarks ModelPicker uses to evaluate models.
list_models — Browse the ModelPicker model catalog with optional filters.
get_model — Get full details for a specific model including all benchmark scores, rankings vs other models, and deprecation status.
compare_models — Head-to-head comparison of two models across all benchmarks.
find_alternatives — Find replacement models for a given model.