FieldCure.AssistStudio.Runner 2.0.3

.NET 8.0 This package targets .NET 8.0. The package is compatible with this framework or higher. 
{
  "servers": {
    "FieldCure.AssistStudio.Runner": {
      "type": "stdio",
      "command": "dnx",
      "args": ["FieldCure.AssistStudio.Runner@2.0.3", "--yes"]
    }
  }
}
This package contains an MCP Server. The server can be used in VS Code by copying the generated JSON to your VS Code workspace's .vscode/mcp.json settings file. 
dotnet tool install --global FieldCure.AssistStudio.Runner --version 2.0.3
This package contains a .NET tool you can call from the shell/command line. 
dotnet new tool-manifest
                    


                            if you are setting up this repo
                        

                    

                
dotnet tool install --local FieldCure.AssistStudio.Runner --version 2.0.3
This package contains a .NET tool you can call from the shell/command line. 
#tool dotnet:?package=FieldCure.AssistStudio.Runner&version=2.0.3
                    


                    

                
nuke :add-package FieldCure.AssistStudio.Runner --version 2.0.3

FieldCure.AssistStudio.Runner

Windows-only headless LLM task automation engine — define natural language tasks, schedule them via Windows Task Scheduler (recurring or one-time), and get results delivered through Slack, Telegram, Email, KakaoTalk, or Discord. Runs as an MCP server for task management or standalone for headless execution.

Install

dotnet tool install -g FieldCure.AssistStudio.Runner

The published package is Windows-only because scheduling is implemented via Windows Task Scheduler and credentials are stored in Windows Credential Manager.

Quick Start

# Create runner.json config template
assiststudio-runner config init

# Set API key
assiststudio-runner config set-credential "Claude Sonnet" sk-ant-api03-...

# Start MCP server
assiststudio-runner serve

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "runner": {
      "command": "assiststudio-runner",
      "args": ["serve"]
    }
  }
}

Tools (7)

Tool Description Confirmation
create_task Create a task with prompt, schedule, and MCP servers Required
update_task Modify task fields (partial update) Required
delete_task Delete a task and its history Required
list_tasks List all tasks with last execution status —
run_task Start task execution (async or wait up to 60s) Required
get_task_history Query execution history for a task —
get_execution_status Check status of a running execution —

Execution Modes

Mode Command Purpose
Serve assiststudio-runner serve MCP server for task CRUD + execution
Exec assiststudio-runner exec <task-id> Headless single-task execution
Config assiststudio-runner config <cmd> Credential and configuration management

Requirements

Scheduled tasks are registered with Windows Task Scheduler in interactive mode, so the user must be logged in when the trigger fires.

Designed for AssistStudio

Runner is purpose-built for the AssistStudio ecosystem. Tasks are typically created through natural language conversations in AssistStudio, which handles workflow design, MCP server selection, and tool permissions automatically.

While Runner can be used standalone with Claude Desktop or VS Code (via serve mode), you'll need to construct task parameters (prompt, MCP servers, allowed tools) manually. For the full experience, use AssistStudio.

See Also

Part of the AssistStudio ecosystem.

Product Compatible and additional computed target framework versions.
.NET net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed.  net10.0 was computed.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

This package has no dependencies.

Version Downloads Last Updated
2.0.3 75 5/4/2026
2.0.2 68 5/4/2026
2.0.1 60 5/4/2026
2.0.0 69 5/4/2026
1.4.0 105 4/22/2026
1.3.0 107 4/21/2026
1.2.0 104 4/14/2026
1.1.4 103 4/8/2026
1.1.3 98 4/7/2026
1.1.2 85 4/7/2026
1.1.1 90 4/7/2026
1.1.0 90 4/7/2026
1.0.0 95 4/7/2026
0.5.0 110 4/3/2026
0.4.0 121 4/2/2026
0.3.0 102 3/31/2026
0.2.0 104 3/30/2026
0.1.0 107 3/30/2026

v2.0.3: Stops duplicate output-channel deliveries. End-to-end testing of v2.0.2 surfaced a redundancy bug — when output_channel is configured, the framework auto-sends the final summary AND the LLM also called send_message mid-loop, so users got two messages on KakaoTalk/Slack/Email. Two-layer fix: (1) the headless system prompt now declares the configured output_channel by name and instructs the model not to call send_message for it, since the framework will deliver the final response automatically; failure handling is now explicit (do not retry tool calls more than once, finalize immediately on unrecoverable failure with the error reason in the final response, do not exhaust the round budget retrying); (2) TaskExecutor.TryNotifyAsync inspects the loop's tool-call history and skips the auto-send when the LLM already invoked send_message against the same channel — defence-in-depth against legacy tasks and stubborn models that ignore the prompt guidance.