agentic_plex_workflow
Executes complex Plex requests by chaining multiple tool calls and iterating on results until the requested media task is completed.
Instructions
Multi-step Plex workflows via FastMCP sampling with tool execution (SEP-1577).
The model chooses plex_* tool calls; the server runs them and feeds results back until the model returns a final text answer or max_iterations is reached.
Return Format
ToolResult with content: {"success": bool, "result": {"final_output": str, "iterations": int, "executed_tools": list}}
Examples
await agentic_plex_workflow(workflow_prompt="Show me my movie libraries", available_tools=["plex_library"])
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": {
"workflow_prompt": "<workflow_prompt>",
"available_tools": "<available_tools>"
},
"name": "agentic_plex_workflow"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| max_iterations | No | Maximum sample_step rounds (default 8). | |
| available_tools | Yes | Tool names registered on this server (e.g. plex_library, plex_search, plex_media). | |
| workflow_prompt | Yes | Natural-language goal (e.g. 'List movie libraries, then search for Nolan films'). |