Toolroute runs on your own machine — the client starts it, so there is no endpoint to ping. 1 410 installs a week from npm. Last commit 2 Jul 2026.
Route AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.
Today is the operative word: we check Toolroute every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add toolroute -- npx -y @toolroute/sdk
{
"mcpServers": {
"toolroute": {
"args": [
"-y",
"@toolroute/sdk"
],
"command": "npx"
}
}
}
[mcp_servers.toolroute]
command = "npx"
args = ["-y", "@toolroute/sdk"]
{
"mcpServers": {
"toolroute": {
"args": [
"-y",
"@toolroute/sdk"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"toolroute": {
"args": [
"-y",
"@toolroute/sdk"
],
"command": "npx"
}
}
}
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
LoopPause MCP server — pause agent execution and route human approval requests
Read-only MCP server over 50 book-based agent skills: routes a task to the right framework.
MCP server for AI agents to report infrastructure needs they encounter during task execution
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
Minimal stdio MCP server for parallel task execution by AI agents.
WasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API.
MCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.
Answers built from our own checks of this server.