trace_run

GliderMCP

┌ ┐

└ ┘

│

┌ ┐

[solution]

Runs a command under the workspace, captures stdout/stderr evidence, and stores a GliderTrace runtime session.

Why this tool exists

A single failing command can produce stdout, stderr, exit code, logs, counters, and trace artifacts.

How it helps the agent

The model gets one session id with normalized findings instead of a pile of unrelated terminal output.

Try it locally in the GliderTrace playground

Parameters

Name	Type	Required	Description
command	string	Yes	Command executable to run.
arguments	json	No	Optional command arguments.
workingDirectory	string	No	Optional working directory under the workspace root. Defaults to the workspace root.
environment	json	No	Optional environment variables to set for the command process.
captureStdout	boolean	No	Capture stdout as a sensitive artifact. Defaults to true.
captureStderr	boolean	No	Capture stderr as a sensitive artifact. Defaults to true.
collectTrace	boolean	No	Collect a runtime.nettrace artifact with built-in EventPipe collection. Mutually exclusive with collectCounters.
collectCounters	boolean	No	Collect a counters.csv artifact with dotnet-counters. Mutually exclusive with collectTrace.

Examples

Run dotnet test and store command evidence

Request 
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "trace_run",
    "arguments": {
      "command": "dotnet",
      "arguments": [
        "test",
        "MyApp.sln"
      ]
    }
  }
}

Response Notes

Returns a stored session id, command status, exit code, artifact references, findings, and timeout metadata.

└ ┘