Skip to main content
Glama

Set up + launch the on-prem runner on this machine

setup_runner

Downloads, validates, builds, and launches an on-prem runner on this machine for a SignalR block, ready for handler testing and endpoint deployment.

Instructions

Stands the on-prem runner up ON THIS MACHINE for a SignalR block, end-to-end: downloads the ready-to-run project (the handler baked in), validates its integrity manifest, preserves machine-local settings, writes it to ~/.qu4zr/runners//, builds it with dotnet, then onboards + launches it in TEST MODE in the background. Failures identify integrity, local config, SDK, generated plumbing, handler, or generic build stages. Once it's up, call test_runner_handler to verify/iterate, then deploy_endpoint to publish. REQUIRES confirm:true — it runs UNSANDBOXED AI-written C# on the user's machine. Needs the .NET SDK ('dotnet') installed. Show the user Handler.cs (returned) so they can review what will run. Pass installService:true to instead install it as an always-on OS service (survives reboots) — this triggers an admin/UAC prompt the USER must approve; suggest it once the endpoint is verified + deployed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "signalRBlockId": "<signalRBlockId>"
    },
    "name": "setup_runner"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNoLaunch after building (default true). false = download + build only, then tell the user the command to run.
confirmNoMust be true: downloads, builds, and LAUNCHES unsandboxed C# on this machine.
installServiceNoInstead of a foreground launch, install the runner as an always-on OS service (admin/UAC prompt the user approves). Use for survive-reboot.
signalRBlockIdYesThe SignalR block's guid (its signalRGuid).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does: it discloses that it runs UNSANDBOXED AI-written C# on the user's machine, mandates confirm:true, specifies background/test-mode launch, lists the failure stages (integrity, local config, SDK, generated plumbing, handler, build), and warns that installService triggers a UAC prompt the user must approve.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical constraint (ON THIS MACHINE, on-prem, end-to-end) is front-loaded, and sentences are dense with actionable content. It is a long, run-on block of colon-and-paren clauses that could be split for scannability, but nearly every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a multi-stage, side-effecting setup tool with no output schema, the description covers the full lifecycle, prerequisites, failure stages, the object returned (Handler.cs for user review), and the next tools to call. Nothing an agent needs to invoke it safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already documented in the schema; the baseline is 3. The description adds real rationale for confirm and installService (UAC prompt, survive-reboot tradeoff) and mentions the returned Handler.cs, but never explains the `run` parameter's false mode beyond the implicit build-only path already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Stands the on-prem runner up ON THIS MACHINE for a SignalR block, end-to-end") and enumerates the concrete pipeline: download, validate manifest, preserve settings, write to ~/.qu4zr/runners/<id>/, build with dotnet, launch in test mode. It is clearly distinguishable from siblings like list_runner_clients or get_runner_release_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit sequencing guidance is given against named siblings: "Once it's up, call test_runner_handler to verify/iterate, then deploy_endpoint to publish." It also names the alternative mode (installService:true) and when to suggest it ("once the endpoint is verified + deployed"), plus the prerequisite that the .NET SDK must be installed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.