Transcodely

Official15 tools

by transcodely · JavaScript

Transcode, host and caption video from a prompt. Fifteen tools, nine read-only, nothing deletes.

Transcodely MCP Server (com.transcodely/mcp)

Transcode and host video for AI agents via the Model Context Protocol (MCP). The server accepts a single natural-language prompt to transcode, host, and return a playable link. It is agent-native and designed to work over MCP, with OAuth used for connection.

🛠️ Key Features

Video transcoding
Video hosting
Returns a playable link “back” from one natural-language prompt

🚀 Use Cases

Provide playable, transcoded video outputs to AI agents
Enable agent workflows that request video processing through MCP

⚡ Developer Benefits

Agent-native integration “over MCP”
Connection via “one OAuth click,” avoiding manual API key creation/paste

⚠️ Limitations

Source material describes connection and core flow, but does not specify supported formats, transcoding options, or performance constraints.

Topics

ai-agentsclaudemcpmcp-servermodel-context-protocolvideo-hostingvideo-transcoding

Declared in the repository manifest (tools.json). Not verified against a live endpoint.

create_job

Create a transcoding job. Reads a source video from a URL (gs://, s3://, or https://) and produces one or more output renditions. Outputs are written to a storage origin you own (pass output_origin_id); to produce a hosted, playable video instead, use create_video_from_url. Returns the job id, status, and a per-output pricing/status summary. Validation (codec x container compatibility, limits, required fields) is performed server-side and surfaced as a machine-readable error.

Parameters7

input_url	string	required	Source video to transcode. Supported schemes: gs:// (Google Cloud Storage), s3:// (S3-compatible), https://.
metadata	object	optional	Arbitrary string key/value pairs echoed back on the job.
output_origin_id	string	optional	Storage origin (ori_...) to write outputs to. Required unless the job targets managed hosting; a job without it is rejected with output_origin_id required.
outputs	null \| array	required	Output renditions to produce (1-10).
preset	string	optional	Preset applied to every output as a base (id like pst_xxx or slug like gaming_1080p_60_standard). Per-output fields override it.
priority	string	optional	Scheduling priority: economy, standard (default), or premium. Does not affect cost.
webhook_url	string	optional	HTTPS endpoint to receive job lifecycle webhook events (job.completed, job.failed, ...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "input_url": {
      "description": "Source video to transcode. Supported schemes: gs:// (Google Cloud Storage), s3:// (S3-compatible), https://.",
      "type": "string"
    },
    "metadata": {
      "additionalProperties": {
        "type": "string"
      },
      "description": "Arbitrary string key/value pairs echoed back on the job.",
      "type": "object"
    },
    "output_origin_id": {
      "description": "Storage origin (ori_...) to write outputs to. Required unless the job targets managed hosting; a job without it is rejected with output_origin_id required.",
      "type": "string"
    },
    "outputs": {
      "description": "Output renditions to produce (1-10).",
      "items": {
        "additionalProperties": false,
        "properties": {
          "format": {
            "description": "Container or packaging format: mp4, webm, mkv, mov, hls, dash, or adaptive.",
            "type": "string"
          },
          "path": {
            "description": "Output path template override for this rendition (e.g. \"{job_id}/{output_id}/video.mp4\").",
            "type": "string"
          },
          "preset": {
            "description": "Preset applied to this output as a base (id like pst_xxx or slug). Overrides the job-level preset; the fields above override the preset.",
            "type": "string"
          },
          "quality_tier": {
            "description": "Quality tier: economy, standard (default), or premium. Higher tiers cost more.",
            "type": "string"
          },
          "resolution": {
            "description": "Target resolution: 480p, 720p, 1080p, 1440p, 2160p, or 4320p. Omit to keep the source resolution or inherit from a preset.",
            "type": "string"
          },
          "video_codec": {
            "description": "Video codec: h264 (default), h265, vp9, or av1. Must be compatible with the chosen format.",
            "type": "string"
          }
        },
        "required": [
          "format"
        ],
        "type": "object"
      },
      "type": [
        "null",
        "array"
      ]
    },
    "preset": {
      "description": "Preset applied to every output as a base (id like pst_xxx or slug like gaming_1080p_60_standard). Per-output fields override it.",
      "type": "string"
    },
    "priority": {
      "description": "Scheduling priority: economy, standard (default), or premium. Does not affect cost.",
      "type": "string"
    },
    "webhook_url": {
      "description": "HTTPS endpoint to receive job lifecycle webhook events (job.completed, job.failed, ...).",
      "type": "string"
    }
  },
  "required": [
    "input_url",
    "outputs"
  ],
  "type": "object"
}

create_preset

Create a custom encoding preset for this app: a named, reusable bundle of encoding settings that create_job can reference by slug. Requires a slug (lowercase letters, digits and underscores, 3-64 characters, permanent once created and unique within the app), a name, a container and video/audio settings. Creating a preset changes nothing about jobs that already exist: presets are read and expanded when a job is created, so a preset only affects jobs created after it. Repeating the call with the same slug fails with already_exists rather than creating a second one.

Parameters13

audio	object	required	Audio encoding settings.
container	string	required	Container format: mp4, webm, mkv, or mov.
content_type	null \| string	optional	Content type for encoder tuning: film, animation, grain, gaming, sports, or stillimage.
delivery_format	string	optional	Delivery format: progressive, hls, dash, or cmaf.
description	string	optional	Optional description (up to 1024 characters).
disable_audio	null \| boolean	optional	Produce video-only outputs (no audio). Defaults to false.
faststart	null \| boolean	optional	Move the MP4 index to the front for progressive playback. Defaults to true.
name	string	required	Human-readable name (1-128 characters).
quality_tier	string	optional	Quality tier: economy, standard (default), or premium.
segment_duration	null \| integer	optional	Segment duration in seconds for hls/dash (2-30, default 6).
slug	string	required	URL-safe identifier, unique within the app and permanent once created. Lowercase letters, digits and underscores only, 3-64 characters (e.g. "gaming_1080p_60").
variants	null \| array	optional	Multi-variant ABR ladder (up to 20 rungs). Only valid when delivery_format is hls, dash or cmaf.
video	object	required	Video encoding settings.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "audio": {
      "additionalProperties": false,
      "description": "Audio encoding settings.",
      "properties": {
        "bitrate_kbps": {
          "description": "Audio bitrate in kbps.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": "integer"
        },
        "channels": {
          "description": "Channel count. Omit to keep the source's.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "codec": {
          "description": "Audio codec: aac (default), opus, mp3, or flac.",
          "enum": [
            "aac",
            "opus",
            "mp3",
            "flac"
          ],
          "type": "string"
        },
        "normalize": {
          "description": "Apply loudness normalization.",
          "type": "boolean"
        },
        "sample_rate": {
          "description": "Sample rate in Hz. Omit to keep the source's.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        }
      },
      "type": "object"
    },
    "container": {
      "description": "Container format: mp4, webm, mkv, or mov.",
      "enum": [
        "mp4",
        "webm",
        "mkv",
        "mov"
      ],
      "type": "string"
    },
    "content_type": {
      "description": "Content type for encoder tuning: film, animation, grain, gaming, sports, or stillimage.",
      "enum": [
        "film",
        "animation",
        "grain",
        "gaming",
        "sports",
        "stillimage"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "delivery_format": {
      "description": "Delivery format: progressive, hls, dash, or cmaf.",
      "enum": [
        "progressive",
        "hls",
        "dash",
        "cmaf"
      ],
      "type": "string"
    },
    "description": {
      "description": "Optional description (up to 1024 characters).",
      "type": "string"
    },
    "disable_audio": {
      "description": "Produce video-only outputs (no audio). Defaults to false.",
      "type": [
        "null",
        "boolean"
      ]
    },
    "faststart": {
      "description": "Move the MP4 index to the front for progressive playback. Defaults to true.",
      "type": [
        "null",
        "boolean"
      ]
    },
    "name": {
      "description": "Human-readable name (1-128 characters).",
      "type": "string"
    },
    "quality_tier": {
      "description": "Quality tier: economy, standard (default), or premium.",
      "enum": [
        "economy",
        "standard",
        "premium"
      ],
      "type": "string"
    },
    "segment_duration": {
      "description": "Segment duration in seconds for hls/dash (2-30, default 6).",
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": [
        "null",
        "integer"
      ]
    },
    "slug": {
      "description": "URL-safe identifier, unique within the app and permanent once created. Lowercase letters, digits and underscores only, 3-64 characters (e.g. \"gaming_1080p_60\").",
      "type": "string"
    },
    "variants": {
      "description": "Multi-variant ABR ladder (up to 20 rungs). Only valid when delivery_format is hls, dash or cmaf.",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bitrate_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "buffer_size_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "crf": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "framerate": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "height": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "max_bitrate_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "quality": {
            "description": "Per-rung quality tier override: economy, standard, or premium.",
            "enum": [
              "economy",
              "standard",
              "premium"
            ],
            "type": [
              "null",
              "string"
            ]
          },
          "resolution": {
            "description": "Resolution for this rung: 480p, 720p, 1080p, 1440p, 2160p, or 4320p.",
            "enum": [
              "480p",
              "720p",
              "1080p",
              "1440p",
              "2160p",
              "4320p"
            ],
            "type": "string"
          },
          "width": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          }
        },
        "required": [
          "resolution"
        ],
        "type": "object"
      },
      "type": [
        "null",
        "array"
      ]
    },
    "video": {
      "additionalProperties": false,
      "description": "Video encoding settings.",
      "properties": {
        "aq_mode": {
          "description": "Adaptive quantization mode (0-3).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "aq_strength": {
          "description": "Adaptive quantization strength (0.0-3.0).",
          "type": [
            "null",
            "number"
          ]
        },
        "bframes": {
          "description": "Number of B-frames (0-16).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "bitrate_kbps": {
          "description": "Target bitrate in kbps for cbr/vbr (100-100000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "bitrate_mode": {
          "description": "Rate control: crf (quality-targeted), vbr, or cbr.",
          "enum": [
            "crf",
            "cbr",
            "vbr"
          ],
          "type": "string"
        },
        "buffer_size_kbps": {
          "description": "VBV buffer size in kbps (100-480000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "codec": {
          "description": "Video codec: h264 (default), h265, vp9, or av1.",
          "enum": [
            "h264",
            "h265",
            "vp9",
            "av1"
          ],
          "type": "string"
        },
        "crf": {
          "description": "Constant Rate Factor; lower is higher quality and larger files. 15-35 for h264, 18-35 for h265, 15-50 for vp9, 20-55 for av1.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "deblock": {
          "description": "Deblocking filter, \"alpha:beta\" (e.g. \"0:0\").",
          "type": [
            "null",
            "string"
          ]
        },
        "encoder_preset": {
          "description": "Encoder speed preset. h264/h265: ultrafast, superfast, veryfast, faster, fast, medium, slow, slower. av1: \"3\"-\"12\".",
          "type": [
            "null",
            "string"
          ]
        },
        "framerate": {
          "description": "Target frame rate (0 = keep the source's, max 240).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "height": {
          "description": "Custom output height in pixels (128-4320).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "keyint": {
          "description": "GOP size in frames (1-600).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "level": {
          "description": "Codec level, e.g. \"3.0\", \"4.0\", \"5.1\".",
          "type": [
            "null",
            "string"
          ]
        },
        "max_bitrate_kbps": {
          "description": "VBV maximum bitrate in kbps (100-240000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "min_keyint": {
          "description": "Minimum keyframe interval (1-60).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "profile": {
          "description": "Codec profile: baseline, main or high for h264; main or main10 for h265.",
          "type": [
            "null",
            "string"
          ]
        },
        "psy_rd": {
          "description": "Psychovisual rate-distortion, \"strength:trellis\" (e.g. \"1.0:0.0\").",
          "type": [
            "null",
            "string"
          ]
        },
        "rc_lookahead": {
          "description": "Rate-control lookahead frames (0-250).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "refs": {
          "description": "Number of reference frames (1-16).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "resolution": {
          "description": "Target resolution: 480p, 720p, 1080p, 1440p, 2160p, or 4320p. Omit to keep the source resolution. Use this OR width+height.",
          "enum": [
            "480p",
            "720p",
            "1080p",
            "1440p",
            "2160p",
            "4320p"
          ],
          "type": [
            "null",
            "string"
          ]
        },
        "tune": {
          "description": "Content-aware tuning. h264: film, animation, grain, stillimage, fastdecode. h265: grain, fastdecode.",
          "type": [
            "null",
            "string"
          ]
        },
        "width": {
          "description": "Custom output width in pixels (128-7680). Use with height for non-standard aspect ratios.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        }
      },
      "type": "object"
    }
  },
  "required": [
    "slug",
    "name",
    "container",
    "video",
    "audio"
  ],
  "type": "object"
}

create_video_from_url

Ingest a remote https:// video and host it in one call — this is the tool for "transcode and host this, give me a link". Downloads the URL, transcodes it into an adaptive streaming ladder, and returns a hosted video (vid_...) with status "processing". The URL must be publicly reachable over http(s); private/internal targets are rejected (SSRF protection). Visibility follows the app's hosting default, "unlisted" when the app has not set one (playable by anyone with the link, not listed publicly). Enables managed hosting for the app on first use — a one-way change, after which hosted storage and egress bill at the standard rates. To finish the job: poll get_video with the returned id every ~10s until status is "ready" (typically under a few minutes for a short clip), then give the user playback.player_url — that is the durable, clickable link.

Parameters6

description	string	optional	Longer description for the hosted video.
preset	string	optional	Preset (id like pst_xxx or slug) driving the transcode. Omit to use the app's default adaptive ladder.
tags	null \| array	optional	Freeform tags to attach to the video.
title	string	optional	Display title for the hosted video.
url	string	required	Publicly reachable https:// source video to ingest. Private/internal hosts are rejected (SSRF protection).
visibility	string	optional	Access level: public, unlisted, or private. Omit to use the app's hosting default visibility (unlisted if the app has not set one).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "description": {
      "description": "Longer description for the hosted video.",
      "type": "string"
    },
    "preset": {
      "description": "Preset (id like pst_xxx or slug) driving the transcode. Omit to use the app's default adaptive ladder.",
      "type": "string"
    },
    "tags": {
      "description": "Freeform tags to attach to the video.",
      "items": {
        "type": "string"
      },
      "type": [
        "null",
        "array"
      ]
    },
    "title": {
      "description": "Display title for the hosted video.",
      "type": "string"
    },
    "url": {
      "description": "Publicly reachable https:// source video to ingest. Private/internal hosts are rejected (SSRF protection).",
      "type": "string"
    },
    "visibility": {
      "description": "Access level: public, unlisted, or private. Omit to use the app's hosting default visibility (unlisted if the app has not set one).",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "type": "object"
}

generate_captions

Generate AI captions (subtitles) for a hosted video by id (vid_...). Creates a billable captions job: speech is transcribed into a WebVTT subtitle track in the given language (default "auto" to detect the spoken language), attached to the video when the job completes. Billed per source minute; the fee is only charged when a caption track is actually delivered. Idempotent per video+language: repeating the call returns the existing job instead of creating and billing a new one.

Parameters2

language	string	optional	ISO 639-2 language code for the captions (e.g. eng, spa, bul). Defaults to "auto" to detect the spoken language.
video_id	string	required	Hosted video id to caption (vid_...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "language": {
      "description": "ISO 639-2 language code for the captions (e.g. eng, spa, bul). Defaults to \"auto\" to detect the spoken language.",
      "type": "string"
    },
    "video_id": {
      "description": "Hosted video id to caption (vid_...).",
      "type": "string"
    }
  },
  "required": [
    "video_id"
  ],
  "type": "object"
}

get_ingest_rule

Fetch one ingest rule by id (ing_...): its origin, enabled state, filters, the job it submits, and its event/job counts. No secret material is returned — a rule's inbound secret is shown once, when it is created or rotated, and never by this server.

Parameters1

string

required

Ingest rule to fetch (ing_...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "id": {
      "description": "Ingest rule to fetch (ing_...).",
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "type": "object"
}

get_job_status

Get a concise status snapshot for a transcoding job by id (job_...): overall status and progress, any error code/message, and per-output status/progress with errors. Each measured output also carries a report summary — whether the produced file matched the request, which properties differ if it did not, and its codec, resolution and duration. Lighter than the full job record — use it to poll a job to completion.

Parameters1

string

required

Job id to inspect (job_...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "id": {
      "description": "Job id to inspect (job_...).",
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "type": "object"
}

get_output_report

Get the full measurement report for one job output (job_... plus out_...): what the produced file turned out to BE, measured from the written file, and the verdict of comparing that against what the job asked for. Returns the container, the video stream (codec, profile, level, pixel format, dimensions, frame rate, bitrate, color signaling, HDR format), every audio stream, the measured duration, and — when the verdict is that it does not match — each differing property with its expected and actual value. Use it when get_job_status reports a mismatch and you need the values, or to confirm an encode really delivered what was requested. measured is false when the output has no report yet (still running, or it produced no file); that is not an error.

Parameters2

job_id	string	required	Job that produced the output (job_...).
output_id	string	required	Output to report on (out_...), as returned by create_job or get_job_status.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "job_id": {
      "description": "Job that produced the output (job_...).",
      "type": "string"
    },
    "output_id": {
      "description": "Output to report on (out_...), as returned by create_job or get_job_status.",
      "type": "string"
    }
  },
  "required": [
    "job_id",
    "output_id"
  ],
  "type": "object"
}

get_usage

Return hosting usage and cost for a billing month: videos encoded, encoding minutes, average storage, egress, request counts, and per-line and total cost in EUR. Defaults to the current month; pass month as "YYYY-MM" for a specific period.

Parameters1

month

string

optional

Billing month as "YYYY-MM" (e.g. 2026-07). Defaults to the current UTC month.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "month": {
      "description": "Billing month as \"YYYY-MM\" (e.g. 2026-07). Defaults to the current UTC month.",
      "type": "string"
    }
  },
  "type": "object"
}

get_video

Fetch a hosted video by id (vid_...): status, visibility, title, duration, poster image, encoded renditions (resolution, codec, bitrate, dimensions), and — once status is "ready" — a playback block. Poll this until status is "ready" (statuses: uploading, processing, ready, error); no playback block is present before then. playback.player_url is the durable player page to hand a human, and is issued for public and unlisted videos only — private videos are not served by the player page and get playback.hls_url instead, a signed manifest for your own player that stops working at playback.expires_at (re-fetch with get_video rather than storing it).

Parameters1

string

required

Hosted video id to fetch (vid_...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "id": {
      "description": "Hosted video id to fetch (vid_...).",
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "type": "object"
}

list_ingest_events

List the storage deliveries this app's ingest rules received, newest first, with what became of each: the bucket and object key, the outcome (received, matched, created, skipped or failed), the REASON for a skip or failure, and the job id when one was created. This is the direct answer to "I uploaded a file and no job appeared". Filter by rule_id or status.

Parameters4

limit	integer	optional	Maximum events to return (1-100). Defaults to 20.
offset	integer	optional	Number of events to skip, for paging.
rule_id	string	optional	Only events for this rule (ing_...).
status	string	optional	Only events with this outcome: received, matched, created, skipped, or failed.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "limit": {
      "description": "Maximum events to return (1-100). Defaults to 20.",
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": "integer"
    },
    "offset": {
      "description": "Number of events to skip, for paging.",
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": "integer"
    },
    "rule_id": {
      "description": "Only events for this rule (ing_...).",
      "type": "string"
    },
    "status": {
      "description": "Only events with this outcome: received, matched, created, skipped, or failed.",
      "type": "string"
    }
  },
  "type": "object"
}

list_ingest_rules

List this app's ingest rules: the standing instructions that turn an object landing in a storage origin into a transcoding job. Each rule carries the origin it watches, whether it is enabled, the filters an object must satisfy (key prefix, suffixes, content types, size bounds), the job it submits, and its running event/job counts. Start here when an upload did not become a job: a disabled rule still receives events and skips every one. No secret material is returned.

Parameters4

enabled	null \| boolean	optional	Only enabled rules (true) or only disabled ones (false). Omit for both.
limit	integer	optional	Maximum rules to return (1-100). Defaults to 20.
offset	integer	optional	Number of rules to skip, for paging.
origin_id	string	optional	Only rules on this storage origin (ori_...).

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "enabled": {
      "description": "Only enabled rules (true) or only disabled ones (false). Omit for both.",
      "type": [
        "null",
        "boolean"
      ]
    },
    "limit": {
      "description": "Maximum rules to return (1-100). Defaults to 20.",
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": "integer"
    },
    "offset": {
      "description": "Number of rules to skip, for paging.",
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": "integer"
    },
    "origin_id": {
      "description": "Only rules on this storage origin (ori_...).",
      "type": "string"
    }
  },
  "type": "object"
}

list_jobs

List transcoding jobs for the authenticated app, newest first. Optionally filter by status. Returns compact rows (id, status, progress, input_url, cost, timestamps) plus next_cursor for pagination; pass it back as cursor to fetch the next page.

Parameters3

cursor	string	optional	Pagination cursor from a previous response's next_cursor. Omit for the first page.
limit	integer	optional	Maximum jobs to return (1-100). Defaults to 20.
status	string	optional	Filter by job status: pending, probing, processing, completed, failed, canceled, partial, or awaiting_confirmation. Omit for all statuses.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "cursor": {
      "description": "Pagination cursor from a previous response's next_cursor. Omit for the first page.",
      "type": "string"
    },
    "limit": {
      "description": "Maximum jobs to return (1-100). Defaults to 20.",
      "type": "integer"
    },
    "status": {
      "description": "Filter by job status: pending, probing, processing, completed, failed, canceled, partial, or awaiting_confirmation. Omit for all statuses.",
      "type": "string"
    }
  },
  "type": "object"
}

list_presets

List the encoding presets available to this app: the read-only ones the platform ships and the app's own custom ones. Each preset carries its full settings (container, delivery format, video and audio encoding, quality tier, ABR ladder) and an estimated cost per source minute where one can be computed. Filter by content_type, quality_tier, video_codec or delivery_format; pass include_system false for custom presets only. Reference a preset from create_job by its id (pst_...) or its slug.

Parameters7

content_type	null \| string	optional	Filter by content type: film, animation, grain, gaming, sports, or stillimage.
delivery_format	null \| string	optional	Filter by delivery format: progressive, hls, dash, or cmaf.
include_system	null \| boolean	optional	Include the read-only presets the platform ships. Defaults to true.
limit	integer	optional	Maximum presets to return (1-100). Defaults to 20.
offset	integer	optional	Number of presets to skip, for paging. Defaults to 0.
quality_tier	null \| string	optional	Filter by quality tier: economy, standard, or premium.
video_codec	null \| string	optional	Filter by video codec: h264, h265, vp9, or av1.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "content_type": {
      "description": "Filter by content type: film, animation, grain, gaming, sports, or stillimage.",
      "enum": [
        "film",
        "animation",
        "grain",
        "gaming",
        "sports",
        "stillimage"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "delivery_format": {
      "description": "Filter by delivery format: progressive, hls, dash, or cmaf.",
      "enum": [
        "progressive",
        "hls",
        "dash",
        "cmaf"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "include_system": {
      "description": "Include the read-only presets the platform ships. Defaults to true.",
      "type": [
        "null",
        "boolean"
      ]
    },
    "limit": {
      "description": "Maximum presets to return (1-100). Defaults to 20.",
      "type": "integer"
    },
    "offset": {
      "description": "Number of presets to skip, for paging. Defaults to 0.",
      "type": "integer"
    },
    "quality_tier": {
      "description": "Filter by quality tier: economy, standard, or premium.",
      "enum": [
        "economy",
        "standard",
        "premium"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "video_codec": {
      "description": "Filter by video codec: h264, h265, vp9, or av1.",
      "enum": [
        "h264",
        "h265",
        "vp9",
        "av1"
      ],
      "type": [
        "null",
        "string"
      ]
    }
  },
  "type": "object"
}

set_spend_limit

Set or clear this app's monthly transcoding spend limit, in EUR. Requires an organization owner or admin signed in through the browser; API-key sessions cannot change it. Pass monthly_spend_limit_eur to set a limit (greater than 0), or clear: true to remove this app's own limit — one or the other, never both and never neither. Returns the previous and the new EFFECTIVE limit with the rung it comes from, plus the current period's spend: a limit set above a plan or platform ceiling stores fine and changes nothing, because the lower ceiling still binds. Lowering the limit below the period's spend blocks the NEXT job; jobs already queued or running are never stopped.

Parameters2

clear	boolean	optional	Set true to remove this app's own spend limit. A plan or platform ceiling, if one applies, still binds. Supply this OR monthly_spend_limit_eur, never both.
monthly_spend_limit_eur	null \| number	optional	New monthly transcoding spend limit for this app, in EUR. Must be greater than 0. Supply this OR clear, never both.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "clear": {
      "description": "Set true to remove this app's own spend limit. A plan or platform ceiling, if one applies, still binds. Supply this OR monthly_spend_limit_eur, never both.",
      "type": "boolean"
    },
    "monthly_spend_limit_eur": {
      "description": "New monthly transcoding spend limit for this app, in EUR. Must be greater than 0. Supply this OR clear, never both.",
      "type": [
        "null",
        "number"
      ]
    }
  },
  "type": "object"
}

update_preset

Update a custom preset's settings by id (pst_...). Only the fields you supply change; the rest keep their current values, and a setting inside video or audio cannot be cleared through this tool, only replaced. Supplying variants replaces the whole ABR ladder. System presets are read-only and are refused. Running and queued jobs are NOT affected — a job resolves its preset when it is created, so an edit only reaches jobs created after it.

Parameters14

audio	null \| object	optional	Audio settings to change. Fields you omit inside this object keep their current value.
container	null \| string	optional
content_type	null \| string	optional
delivery_format	null \| string	optional
description	null \| string	optional	New description (up to 1024 characters).
disable_audio	null \| boolean	optional
faststart	null \| boolean	optional
id	string	required	Preset to update (pst_...). System presets are read-only.
name	null \| string	optional	New name (1-128 characters).
quality_tier	null \| string	optional
segment_duration	null \| integer	optional
slug	null \| string	optional	New slug. Lowercase letters, digits and underscores only, 3-64 characters.
variants	null \| array	optional	Replaces the whole ABR ladder (up to 20 rungs). Omit to leave it unchanged.
video	null \| object	optional	Video settings to change. Fields you omit inside this object keep their current value; a setting cannot be cleared through this tool, only replaced.

Raw schema

{
  "additionalProperties": false,
  "properties": {
    "audio": {
      "additionalProperties": false,
      "description": "Audio settings to change. Fields you omit inside this object keep their current value.",
      "properties": {
        "bitrate_kbps": {
          "description": "Audio bitrate in kbps.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": "integer"
        },
        "channels": {
          "description": "Channel count. Omit to keep the source's.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "codec": {
          "description": "Audio codec: aac (default), opus, mp3, or flac.",
          "enum": [
            "aac",
            "opus",
            "mp3",
            "flac"
          ],
          "type": "string"
        },
        "normalize": {
          "description": "Apply loudness normalization.",
          "type": "boolean"
        },
        "sample_rate": {
          "description": "Sample rate in Hz. Omit to keep the source's.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        }
      },
      "type": [
        "null",
        "object"
      ]
    },
    "container": {
      "enum": [
        "mp4",
        "webm",
        "mkv",
        "mov"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "content_type": {
      "enum": [
        "film",
        "animation",
        "grain",
        "gaming",
        "sports",
        "stillimage"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "delivery_format": {
      "enum": [
        "progressive",
        "hls",
        "dash",
        "cmaf"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "description": {
      "description": "New description (up to 1024 characters).",
      "type": [
        "null",
        "string"
      ]
    },
    "disable_audio": {
      "type": [
        "null",
        "boolean"
      ]
    },
    "faststart": {
      "type": [
        "null",
        "boolean"
      ]
    },
    "id": {
      "description": "Preset to update (pst_...). System presets are read-only.",
      "type": "string"
    },
    "name": {
      "description": "New name (1-128 characters).",
      "type": [
        "null",
        "string"
      ]
    },
    "quality_tier": {
      "enum": [
        "economy",
        "standard",
        "premium"
      ],
      "type": [
        "null",
        "string"
      ]
    },
    "segment_duration": {
      "maximum": 2147483647,
      "minimum": -2147483648,
      "type": [
        "null",
        "integer"
      ]
    },
    "slug": {
      "description": "New slug. Lowercase letters, digits and underscores only, 3-64 characters.",
      "type": [
        "null",
        "string"
      ]
    },
    "variants": {
      "description": "Replaces the whole ABR ladder (up to 20 rungs). Omit to leave it unchanged.",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bitrate_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "buffer_size_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "crf": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "framerate": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "height": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "max_bitrate_kbps": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          },
          "quality": {
            "description": "Per-rung quality tier override: economy, standard, or premium.",
            "enum": [
              "economy",
              "standard",
              "premium"
            ],
            "type": [
              "null",
              "string"
            ]
          },
          "resolution": {
            "description": "Resolution for this rung: 480p, 720p, 1080p, 1440p, 2160p, or 4320p.",
            "enum": [
              "480p",
              "720p",
              "1080p",
              "1440p",
              "2160p",
              "4320p"
            ],
            "type": "string"
          },
          "width": {
            "maximum": 2147483647,
            "minimum": -2147483648,
            "type": [
              "null",
              "integer"
            ]
          }
        },
        "required": [
          "resolution"
        ],
        "type": "object"
      },
      "type": [
        "null",
        "array"
      ]
    },
    "video": {
      "additionalProperties": false,
      "description": "Video settings to change. Fields you omit inside this object keep their current value; a setting cannot be cleared through this tool, only replaced.",
      "properties": {
        "aq_mode": {
          "description": "Adaptive quantization mode (0-3).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "aq_strength": {
          "description": "Adaptive quantization strength (0.0-3.0).",
          "type": [
            "null",
            "number"
          ]
        },
        "bframes": {
          "description": "Number of B-frames (0-16).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "bitrate_kbps": {
          "description": "Target bitrate in kbps for cbr/vbr (100-100000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "bitrate_mode": {
          "description": "Rate control: crf (quality-targeted), vbr, or cbr.",
          "enum": [
            "crf",
            "cbr",
            "vbr"
          ],
          "type": "string"
        },
        "buffer_size_kbps": {
          "description": "VBV buffer size in kbps (100-480000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "codec": {
          "description": "Video codec: h264 (default), h265, vp9, or av1.",
          "enum": [
            "h264",
            "h265",
            "vp9",
            "av1"
          ],
          "type": "string"
        },
        "crf": {
          "description": "Constant Rate Factor; lower is higher quality and larger files. 15-35 for h264, 18-35 for h265, 15-50 for vp9, 20-55 for av1.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "deblock": {
          "description": "Deblocking filter, \"alpha:beta\" (e.g. \"0:0\").",
          "type": [
            "null",
            "string"
          ]
        },
        "encoder_preset": {
          "description": "Encoder speed preset. h264/h265: ultrafast, superfast, veryfast, faster, fast, medium, slow, slower. av1: \"3\"-\"12\".",
          "type": [
            "null",
            "string"
          ]
        },
        "framerate": {
          "description": "Target frame rate (0 = keep the source's, max 240).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "height": {
          "description": "Custom output height in pixels (128-4320).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "keyint": {
          "description": "GOP size in frames (1-600).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "level": {
          "description": "Codec level, e.g. \"3.0\", \"4.0\", \"5.1\".",
          "type": [
            "null",
            "string"
          ]
        },
        "max_bitrate_kbps": {
          "description": "VBV maximum bitrate in kbps (100-240000).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "min_keyint": {
          "description": "Minimum keyframe interval (1-60).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "profile": {
          "description": "Codec profile: baseline, main or high for h264; main or main10 for h265.",
          "type": [
            "null",
            "string"
          ]
        },
        "psy_rd": {
          "description": "Psychovisual rate-distortion, \"strength:trellis\" (e.g. \"1.0:0.0\").",
          "type": [
            "null",
            "string"
          ]
        },
        "rc_lookahead": {
          "description": "Rate-control lookahead frames (0-250).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "refs": {
          "description": "Number of reference frames (1-16).",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        },
        "resolution": {
          "description": "Target resolution: 480p, 720p, 1080p, 1440p, 2160p, or 4320p. Omit to keep the source resolution. Use this OR width+height.",
          "enum": [
            "480p",
            "720p",
            "1080p",
            "1440p",
            "2160p",
            "4320p"
          ],
          "type": [
            "null",
            "string"
          ]
        },
        "tune": {
          "description": "Content-aware tuning. h264: film, animation, grain, stillimage, fastdecode. h265: grain, fastdecode.",
          "type": [
            "null",
            "string"
          ]
        },
        "width": {
          "description": "Custom output width in pixels (128-7680). Use with height for non-standard aspect ratios.",
          "maximum": 2147483647,
          "minimum": -2147483648,
          "type": [
            "null",
            "integer"
          ]
        }
      },
      "type": [
        "null",
        "object"
      ]
    }
  },
  "required": [
    "id"
  ],
  "type": "object"
}

README.md12 KBView on GitHub

Transcodely MCP Server

A video pipeline for AI agents, over the Model Context Protocol — with nothing on it that can delete your work.

smithery badge

Hand your agent a video URL and it comes back a playable link: transcoded into an ABR ladder, hosted, captioned if you ask. Then let it read back what it actually produced, what it cost, and why an upload did not become a job. No delete, no cancel, no key material. Connect with one OAuth click — no API key to create or paste.

Server URL (streamable HTTP): https://mcp.transcodely.com/mcp
Product page: https://www.transcodely.com/mcp
Connect guide: https://www.transcodely.com/docs/guides/mcp
Registry identifier: com.transcodely/mcp

This is the public home of the hosted server: connect instructions, the tool surface, and the registry manifest. The server itself is a hosted service — there is nothing to install or run.

Connect

Claude Code

bash

claude mcp add --transport http transcodely https://mcp.transcodely.com/mcp

Then run /mcp inside Claude Code and pick Authenticate — your browser opens, you approve, and the tools are live. No Transcodely account yet? One is created for you during authorization.

claude.ai / Claude desktop — Settings → Connectors → Add custom connector → https://mcp.transcodely.com/mcp.

Cursor — add to ~/.cursor/mcp.json:

json

{
  "mcpServers": {
    "transcodely": { "type": "http", "url": "https://mcp.transcodely.com/mcp" }
  }
}

Any other client that supports remote MCP servers over streamable HTTP works the same way. For headless use (CI, server-side agents), attach a Transcodely API key as a bearer token instead — see the connect guide.

Tools (15)

Fifteen tools: nine only read, four create something — three of those start work you are billed for, and saving a preset is free — and two overwrite a setting that only affects work created after it. No tool on this surface deletes, cancels, removes or rotates anything.

Tool	Effect	What it does
`create_job`	creates work · billable	Create a transcoding job.
`create_preset`	creates · free	Create a custom encoding preset for this app: a named, reusable bundle of encoding settings that create_job can reference by slug.
`create_video_from_url`	creates work · billable	Ingest a remote https:// video and host it in one call — this is the tool for "transcode and host this, give me a link".
`generate_captions`	creates work · billable	Generate AI captions (subtitles) for a hosted video by id (vid_...).
`get_ingest_rule`	read	Fetch one ingest rule by id (ing_...): its origin, enabled state, filters, the job it submits, and its event/job counts.
`get_job_status`	read	Get a concise status snapshot for a transcoding job by id (job_...): overall status and progress, any error code/message, and per-output status/progress with errors.
`get_output_report`	read	Get the full measurement report for one job output (job_... plus out_...): what the produced file turned out to BE, measured from the written file, and the verdict of comparing that against what the job asked for.
`get_usage`	read	Return hosting usage and cost for a billing month: videos encoded, encoding minutes, average storage, egress, request counts, and per-line and total cost in EUR.
`get_video`	read	Fetch a hosted video by id (vid_...): status, visibility, title, duration, poster image, encoded renditions (resolution, codec, bitrate, dimensions), and — once status is "ready" — a playback block.
`list_ingest_events`	read	List the storage deliveries this app's ingest rules received, newest first, with what became of each: the bucket and object key, the outcome (received, matched, created, skipped or failed), the REASON for a skip or failure, and the job id when one was created.
`list_ingest_rules`	read	List this app's ingest rules: the standing instructions that turn an object landing in a storage origin into a transcoding job.
`list_jobs`	read	List transcoding jobs for the authenticated app, newest first.
`list_presets`	read	List the encoding presets available to this app: the read-only ones the platform ships and the app's own custom ones.
`set_spend_limit`	overwrites a setting	Set or clear this app's monthly transcoding spend limit, in EUR.
`update_preset`	overwrites a setting	Update a custom preset's settings by id (pst_...).

Generated from tools.json by npm run readme:gen — do not edit by hand. Read-only: 9. Writing: 6. Billable: 3.

What the surface cannot do

The promise is narrow and literal, and it is checked rather than asserted: test/vendored.mjs re-derives it from tools.json on every CI run and fails if a future release adds a tool whose name begins with delete, cancel, remove, purge, rotate or destroy.

Nothing is deleted or cancelled. No tool removes a video, a job, an output, a preset or a rule, and none stops work that is already queued or running. An agent that decides mid-task to "clean up" has no instrument for it.
Nothing reads key or secret material. There is no tool for API keys, and the ingest tools deliberately withhold even the prefix-and-last-four hint the REST API exposes: a rule's inbound secret is shown once, at creation, and never by this server. A tool result lands in an agent transcript, so anything a transcript should not carry is not on the surface at all.
Nothing reaches your organization. Members, plans, invoices, team settings and the admin surface have no tools.
The overwriting pair only ever reaches forward. update_preset and set_spend_limit carry destructiveHint: true, which in the protocol means "replaces a value" rather than "additive" — not that anything is removed. A preset is read and expanded when a job is created, so editing one never reaches a job that already exists; lowering a spend limit blocks the next job and never stops one in flight.

Who can change the spend limit

set_spend_limit is the only tool with an authorization rule of its own, because it is the only one that moves money policy.

It requires an organization owner or admin, signed in through the browser OAuth flow. That is the same membership check the REST API applies, plus one rule REST does not have.
API-key sessions are refused outright — including the stdio bridge below, which authenticates with ak_…. The refusal says so in words rather than failing as a generic permission error. This surface is deliberately stricter than REST here: over REST, a key can manage its own app's limit.
It reads the limit back instead of echoing what it was given: a limit set above a plan or platform ceiling stores fine and changes nothing, because the lower ceiling still binds. The result carries the previous and the new effective limit and the rung it comes from.

Auth and guardrails

OAuth 2.1 with PKCE via browser consent; the server implements RFC 9728 Protected Resource Metadata and RFC 8707 resource indicators.
Every tool call is scoped to one Transcodely app, resolved from the session, never from a tool argument. An agent cannot widen its own scope by passing a different id: a job, video, preset or rule belonging to another app reads back as not found rather than as a permission error, which would confirm it exists. Connect to https://mcp.transcodely.com/mcp/app_… to pin a specific app; the bare URL resolves to your organization's oldest active app.
An ak_… key presented at a different app's URL is rejected outright.
Every call writes the same audit trail as the equivalent REST call.
The MCP server is free to connect. Three tools start billable work — create_job, create_video_from_url and generate_captions — charged at the ordinary Transcodely rates. Every other tool is free to call, including the ones that write: saving a preset or setting a spend limit costs nothing.

Try it

"Transcode and host this video and give me a link: https://www.transcodely.com/videos/bbb-30s.mp4"
"Generate English captions for that video."
"What's the status of my last job?"
"Did that 1080p output actually come out as 1080p h264? Show me the measured report."
"I uploaded a file to my bucket and no job appeared — what happened?"
"How much have I spent on video this month, and which day cost the most?"

Run locally (stdio bridge)

Remote-capable clients should connect straight to the hosted endpoint above — that's the one-click OAuth path. For stdio-only clients, sandboxes, and headless use, this repo is also a runnable bridge that serves the same tools over stdio and forwards calls to the hosted server:

bash

# with an API key (create one in the Transcodely dashboard):
TRANSCODELY_API_KEY=ak_... npx github:transcodely/mcp

# or via Docker:
docker build -t transcodely-mcp .
docker run -i --rm -e TRANSCODELY_API_KEY=ak_... transcodely-mcp

Without TRANSCODELY_API_KEY the bridge still starts and answers introspection (initialize, tools/list); tool calls return an error pointing at the two auth paths. set_spend_limit is listed but always refused over this path — see the rule above.

How `tools.json` is kept honest

tools.json is generated, not written: it is the byte-exact stdout of the Transcodely API's own export, go run ./cmd/mcp --dump-tools, run in a checkout of the release pinned in api-pin.json. The README table above is generated from it in turn. Two checks hold that chain:

Check	Command	Runs
Vendored consistency — counts, annotations, the "nothing deletes" promise, manifest versions, the README naming every tool	`node test/vendored.mjs`	every push and PR
The bridge serves exactly the vendored surface, keyless calls guide	`node test/introspect.mjs`	every push and PR
The README table is regenerated from `tools.json`	`node scripts/gen-readme.mjs --check`	every push and PR
`tools.json` is byte-exact with the pinned api release	`npm run tools:check`	when a token is available — see below

To land a tool-surface change:

bash

# 1. point api-pin.json's "ref" at the release you are vendoring
# 2. read a DETACHED WORKTREE at that tag — never the shared api checkout,
#    which other sessions commit to and which sits on master
git -C ~/git/transcodely/api worktree add --detach /tmp/api-pin v5.X.0
TRANSCODELY_API_PATH=/tmp/api-pin npm run tools:sync
npm run readme:gen
git -C ~/git/transcodely/api worktree remove /tmp/api-pin
# 3. bump the version in server.json + package.json, in the same commit
npm test

Or skip step 2 entirely: with API_REPO_TOKEN set and no TRANSCODELY_API_PATH, the script clones the pinned tag itself. That is the only mode that verifies the pin, so prefer it.

The honest limitation: transcodely/api is a private repository, so the parity job needs a read token in API_REPO_TOKEN and cannot run on a pull request from a fork. When the token is absent the script exits 78 and the job reports not armed rather than passing — it never claims a parity it did not check. The always-on checks above still catch the drift that has actually bitten here: an export that moved while the README, the manifest and the bridge kept the old numbers.

Manifest

server.json is the manifest published to the official MCP registry. Its version must be bumped for a republish to take effect — the registry serves the last published version's description, so a description edit with an unchanged version is invisible.

Install

Tools (15)

create_jobcreate_presetcreate_video_from_urlgenerate_captionsget_ingest_ruleget_job_statusget_output_reportget_usage

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.transcodely.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.transcodely.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Transcodely MCP Server (com.transcodely/mcp)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

create_job

create_preset

create_video_from_url

generate_captions

get_ingest_rule

get_job_status

get_output_report

get_usage

get_video

list_ingest_events

list_ingest_rules

list_jobs

list_presets

set_spend_limit

update_preset

Transcodely MCP Server

Connect

Tools (15)

What the surface cannot do

Who can change the spend limit

Auth and guardrails

Try it

Run locally (stdio bridge)

How tools.json is kept honest

Manifest

Install

Remote endpoint

Related servers

How `tools.json` is kept honest