Skip to main content
Glama

BulkTranscripts YouTube

by co.bulktranscripts
OverviewDiscussionsAdmin

Get many transcripts at once

get_transcripts
Idempotent

Fetch transcripts for up to 20 videos in one call — pass an array of YouTube URLs or ids. Videos are fetched in parallel and the call returns within about 40 seconds; any video still being fetched at that point is listed in failed with code still_fetching, is not charged, and keeps fetching in the background, so a repeat call with those ids 15-30 seconds later returns them instantly. Each new library addition costs 1 credit; repeats from this account's library are free. Videos without captions are reported per-item and do not fail the batch. One call counts as one request against the rate limit however many videos it holds. If the balance runs out, completed items are returned with partial=true and an out_of_credits stopped block.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
videosYesUp to 20 YouTube video URLs or ids.
languageNoPreferred caption language code. Default 'en'.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
failedYes
billingYes
partialNoPresent and true when credits ran out mid-batch.
stoppedNo
requestedYes
succeededYes
transcriptsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "billing": {
+      "properties": {
+        "creditsCharged": {
+          "description": "Credits this call cost (0 on cache hits).",
+          "type": "integer"
+        },
+        "enabled": {
+          "type": "boolean"
+        },
+        "freeLimit": {
+          "type": "integer"
+        },
+        "granted": {
+          "type": "integer"
+        },
+        "kind": {
+          "description": "anon (free tier), license (paid) or admin.",
+          "type": "string"
+        },
+        "remaining": {
+          "description": "Credits left on this account.",
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "unlimited": {
+          "type": "boolean"
+        },
+        "used": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "enabled"
+      ],
+      "type": "object"
+    },
+    "failed": {
+      "items": {
+        "properties": {
+          "error": {
+            "properties": {
+              "code": {
+                "type": "string"
+              },
+              "message": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ],
+            "type": "object"
+          },
+          "video": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "video",
+          "error"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "partial": {
+      "description": "Present and true when credits ran out mid-batch.",
+      "type": "boolean"
+    },
+    "requested": {
+      "type": "integer"
+    },
+    "stopped": {
+      "properties": {
+        "code": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        },
+        "not_attempted": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "code"
+      ],
+      "type": "object"
+    },
+    "succeeded": {
+      "type": "integer"
+    },
+    "transcripts": {
+      "items": {
+        "properties": {
+          "billing": {
+            "properties": {
+              "creditsCharged": {
+                "description": "Credits this call cost (0 on cache hits).",
+                "type": "integer"
+              },
+              "enabled": {
+                "type": "boolean"
+              },
+              "freeLimit": {
+                "type": "integer"
+              },
+              "granted": {
+                "type": "integer"
+              },
+              "kind": {
+                "description": "anon (free tier), license (paid) or admin.",
+                "type": "string"
+              },
+              "remaining": {
+                "description": "Credits left on this account.",
+                "type": [
+                  "integer",
+                  "null"
+                ]
+              },
+              "unlimited": {
+                "type": "boolean"
+              },
+              "used": {
+                "type": "integer"
+              }
+            },
+            "required": [
+              "enabled"
+            ],
+            "type": "object"
+          },
+          "cached": {
+            "description": "True when served from this account's library (free).",
+            "type": "boolean"
+          },
+          "channel": {
+            "type": "string"
+          },
+          "duration": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "duration_text": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "language": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "paragraphs": {
+            "description": "Silence-grouped paragraphs; best for reading and chunking.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "segments": {
+            "description": "Only when include_segments is true.",
+            "items": {
+              "properties": {
+                "duration": {
+                  "type": "number"
+                },
+                "start": {
+                  "type": "number"
+                },
+                "text": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "text",
+                "start"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "source": {
+            "description": "manual_caption or auto_caption.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "text": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "upload_date": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "type": "string"
+          },
+          "video_id": {
+            "type": "string"
+          },
+          "word_count": {
+            "type": "integer"
+          }
+        },
+        "required": [
+          "video_id",
+          "url",
+          "title",
+          "channel",
+          "text",
+          "paragraphs"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "requested",
+    "succeeded",
+    "failed",
+    "transcripts",
+    "billing"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: ~40 second wall clock, per-item failures (still_fetching, no captions) that do not fail the batch, background continuation with free repeat retrieval, 1 credit per new library addition with repeats free, one request per call against the rate limit, and out_of_credits handling with partial=true. This is far richer than the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then each subsequent sentence carries a distinct operational fact (timing, failure codes, cost, rate limit, credit exhaustion) with no filler or repetition.

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

Completeness5/5

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

Although an output schema exists, the description still explains the failure-mode fields (failed, still_fetching, partial, out_of_credits) that matter for correct handling. For a 2-parameter batch tool with annotations and an output schema, nothing an agent needs to call or interpret it is missing.

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

Parameters3/5

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

Schema coverage is 100%, so both parameters are already documented; the description restates the array-of-URLs-or-ids input and the 20-item cap without adding syntax or format detail beyond the schema. Baseline 3 applies since the schema does the heavy lifting, though the free-repeat note adds minor meaning about id reuse.

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

Purpose5/5

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

States a specific verb and resource with explicit scope: 'Fetch transcripts for up to 20 videos in one call.' The batching scope and the URL-or-id input form make it clearly distinct from the single-video sibling get_transcript.

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?

Clearly frames the batch context (multiple videos, one call, one rate-limit request) and gives concrete retry guidance: re-call with the still_fetching ids after 15-30 seconds. It never explicitly names get_transcript as the single-video alternative, so the routing is implied rather than stated.

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

All BulkTranscripts YouTube toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources