Headless LLM task runner — schedule natural language tasks via MCP, execute with any LLM provider, deliver results through Slack/Telegram/Email
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add assiststudio-runner -- dnx FieldCure.AssistStudio.Runner --yes~/.codex/config.toml
[mcp_servers.assiststudio-runner]
command = "dnx"
args = ["FieldCure.AssistStudio.Runner", "--yes"]
# codex mcp add assiststudio-runner -- dnx FieldCure.AssistStudio.Runner --yes~/.cursor/mcp.json
{
"mcpServers": {
"assiststudio-runner": {
"command": "dnx",
"args": [
"FieldCure.AssistStudio.Runner",
"--yes"
]
}
}
}.vscode/mcp.json
{
"servers": {
"assiststudio-runner": {
"type": "stdio",
"command": "dnx",
"args": [
"FieldCure.AssistStudio.Runner",
"--yes"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"assiststudio-runner": {
"command": "dnx",
"args": [
"FieldCure.AssistStudio.Runner",
"--yes"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"assiststudio-runner": {
"command": "dnx",
"args": [
"FieldCure.AssistStudio.Runner",
"--yes"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"assiststudio-runner": {
"command": "dnx",
"args": [
"FieldCure.AssistStudio.Runner",
"--yes"
]
}
}
}