Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add toolroute -- npx -y @toolroute/sdk~/.codex/config.toml
[mcp_servers.toolroute]
command = "npx"
args = ["-y", "@toolroute/sdk"]
# codex mcp add toolroute -- npx -y @toolroute/sdk~/.cursor/mcp.json
{
"mcpServers": {
"toolroute": {
"command": "npx",
"args": [
"-y",
"@toolroute/sdk"
]
}
}
}.vscode/mcp.json
{
"servers": {
"toolroute": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@toolroute/sdk"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"toolroute": {
"command": "npx",
"args": [
"-y",
"@toolroute/sdk"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"toolroute": {
"command": "npx",
"args": [
"-y",
"@toolroute/sdk"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"toolroute": {
"command": "npx",
"args": [
"-y",
"@toolroute/sdk"
]
}
}
}