Skip to main content
Glama
calebn

Podcast MCP

by calebn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

pipeline_run

Run the production pipeline for podcast projects to handle multitrack management, transcription, edits, and audio processing.

Instructions

Run the production pipeline. Optional skip_steps (step names) / config (object) override yaml.

When use_working_set is true (default), also reads/writes the GUI session working set so agents and Sharecut Studio share the same visible config. Omit unattended to leave the working-set Batch mode unchanged. Existing transcripts are reused; force_transcribe=true re-runs ASR for this run only (not persisted). retime_words=true re-times stored transcripts with the forced aligner from their ASR cache for this run only (no Whisper; hand-edited transcripts are skipped); check transcript_timing.json → forced_alignment.retime for skipped and failed tracks; not with force_transcribe. It fails before changing any transcript when the word aligner is not downloaded (the error names podcast bootstrap --component word-aligner). Forced alignment is otherwise on by default whenever that model is installed (transcribe.forced_alignment.enabled unset); forced_alignment.reason in transcript_timing.json says what a run resolved to. Replacing edited transcripts is refused when unattended; run attended, or the user confirms with Studio Re-transcribe. Returns Completed through <step>; when this run exported, the next lines are the export QC verdict (same as CLI pipeline run).

Input Schema

NameRequiredDescriptionDefault
configNo
from_stepNo
only_stepNo
skip_stepsNo
unattendedNo
project_pathNo
retime_wordsNo
use_working_setNo
force_transcribeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.1.1
    • addedInput schema / properties / config
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Config"
+}
    • removedInput schema / properties / config_json
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Config Json"
-}
    • addedInput schema / properties / force_transcribe
      Added value: +{
+  "default": false,
+  "title": "Force Transcribe",
+  "type": "boolean"
+}
    • addedInput schema / properties / project_path / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / project_path / default
      Added value: +null
    • removedInput schema / properties / project_path / type
      Removed value: -"string"
    • addedInput schema / properties / retime_words
      Added value: +{
+  "default": false,
+  "title": "Retime Words",
+  "type": "boolean"
+}
    • addedInput schema / properties / skip_steps
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Skip Steps"
+}
    • removedInput schema / properties / skip_steps_json
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Skip Steps Json"
-}
    • removedInput schema / required
      Removed value: -[
-  "project_path"
-]
  2. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: force_transcribe re-runs ASR for this run only (not persisted), retime_words re-times from ASR cache without Whisper and skips hand-edited transcripts, edits are refused under unattended, and the word-aligner-missing failure names a bootstrap command. Return-value shape is also disclosed.

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?

Front-loaded with purpose before edge cases, and nearly every sentence conveys a behavioral constraint rather than filler. It is dense with nested parentheticals and backticked paths, so it is longer than ideal, but the length is mostly earned by the tool's complexity.

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

Completeness4/5

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

An output schema exists, so return values needn't be spelled out, yet the description still notes the "Completed through <step>" and QC verdict lines. Behavior is well covered for a no-annotation tool; the only shortfall is the unexplained step-selection parameters (from_step, only_step) and project_path.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate; it explains skip_steps, config, use_working_set (default true), unattended (omit to leave Batch mode unchanged), force_transcribe, and retime_words with real behavioral meaning. It leaves from_step, only_step, and project_path entirely undocumented, which is a meaningful gap for step-controlled execution.

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

Purpose4/5

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

The opening sentence gives a specific verb+resource ("Run the production pipeline") and the body clarifies scope (yaml overrides, working-set sharing). It is clearly distinct from siblings like pipeline_analyze_tool or pipeline_get_config_tool, though it never names or contrasts an alternative explicitly.

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

Usage Guidelines4/5

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

Rich conditional guidance: when use_working_set applies, when to omit unattended, when retime_words is refused (unattended), and the recovery path ("run attended, or the user confirms with Studio Re-transcribe"). It stops short of stating when to prefer this tool over pipeline_analyze_tool, so no explicit alternative routing.

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

Deploy Server

Other Tools