Skip to main content
Glama

transcode_video

Destructive

Submit a transcoding job.

Args:
    source: URL of the input video (https://, s3://, or `tus:<uuid>`).
        No credentials in any input URL (`s3://KEY:SECRET@…`,
        `https://user:pass@…`); use a public, presigned GET, or Media
        Storage URL instead.
    outputs: list of format-spec dicts. Each MUST have an `output` field
        whose value is one of: mp4, webm, advanced_hls, advanced_dash,
        webm_dash, repack, mp3, m4a, hls_audio, flac, gif, thumbnail,
        thumbnails, smart_thumbnail, metadata, speech_to_text, vmaf,
        video_intelligence, ai_detection, waveform.
        The OUTER array is named `format` in the Qencode schema (this
        tool wraps it for you). The INNER STRING field naming the type
        is `output` — NOT `format`. This is the most common composition
        mistake. Example of a valid entry:
            {
                "output": "mp4",
                "video_codec": "libx264",
                "audio_codec": "libfdk_aac",
                "resolution": 720,
                "optimize_bitrate": 1,
                "audio_bitrate": 128,
                "destination": {
                    "url": "<destination_prefix>/<new filename or folder>"
                }
            }
        Media Storage `destination.url` is `{destination_prefix}/{new key}`
        — a NEW file or folder, never a listed object's `destination_url`
        (that is the existing file, for reading as `source`). Folder
        outputs (HLS / STT / VI / thumbnails) take `{destination_prefix}/folder`
        with no trailing slash. Do not assemble the host.
        Only Media Storage destinations are accepted: `s3://<bucket>/…`,
        AWS / R2 / Azure / FTP / presigned URLs and any `key`/`secret`
        are rejected. Inputs the encoder fetches (`source`, `distorted`,
        subtitle files, `logo.source`) use `cdn_url` when public and
        `destination_url` when private. Video Intelligence `source` must
        be https — `cdn_url` only; a private object cannot be a VI source.
        For HLS/DASH ABR, put per-rendition params on each entry of an
        inner `stream[]` array (not on the format object directly).
        Output-specific required fields (see matching recipe):
            advanced_hls / advanced_dash / webm_dash / hls_audio —
                non-empty `stream[]` of objects. A bare
                `{"output": "advanced_hls"}` is rejected. Fetch
                `qencode://recipe/hls_abr` (or `audio_outputs` for
                `hls_audio`) before composing.
            vmaf — `distorted` URL of the encoded video; `source` is the
                reference original (encoder v1 is auto-selected).
            video_intelligence — `mode` one of description, categorization,
                moderation, search, custom (NOT `features`). Source must be
                https:// and meet duration minimums (description etc. ≥10s,
                search ≥4s) — check via metadata or tell user if too short.
        Example vmaf entry:
            {
                "output": "vmaf",
                "distorted": "https://example.com/encoded.mp4",
                "destination": {"url": "<destination_prefix>/vmaf.json"}
            }
        Example HLS entry (params on `stream[]`, not on the format object):
            {
                "output": "advanced_hls",
                "segment_duration": 6,
                "stream": [{
                    "video_codec": "libx264",
                    "audio_codec": "libfdk_aac",
                    "resolution": 720,
                    "framerate": "30",
                    "keyframe": "60",
                    "optimize_bitrate": 1,
                    "audio_bitrate": 128
                }]
            }
        Example video_intelligence entry:
            {
                "output": "video_intelligence",
                "mode": "description",
                "destination": {"url": "<destination_prefix>/vi"}
            }
    payload: optional opaque callback tag echoed by Qencode. Must be a
        string (or omitted). A JSON object is not submitted — the tool
        returns `{"error": "..."}` asking you to retry with a string.
        It is not the job body (`outputs` is). Do not put `source` or
        `format` in `payload`.

`encoder_version` is injected automatically when omitted: `2` by default,
`1` when any output is `vmaf`. Stitch jobs (multi-source `stitch` array)
are not supported here — use `start_encode2_raw` with `encoder_version: 2`
per `qencode://recipe/stitching`.

Other composition defaults in this server's instructions (libfdk_aac,
optimize_bitrate, per-stream ABR params, etc.) still belong in each
`outputs[]` entry — consult the matching recipe via
`search_qencode_docs` + `fetch_qencode_doc` before submitting.

After this returns a `task_token`, in the SAME reply call `list_jobs`
with that token. If the job is already Done with a playable video URL,
also `open_player`. If the deliverable is a json/txt/srt/vtt file, call
`fetch_job_result` and give the user both the URL and the extracted
content.

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": {
      "source": "<source>",
      "outputs": "<outputs>"
    },
    "name": "transcode_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYes
outputsYes
payloadNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / payload / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "additionalProperties": true,
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed4 schema fields changed
    • removedOutput schema / additionalProperties
      Removed value: -false
    • addedOutput schema / oneOf
      Added value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "status_url": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "task_token": {
      +        "type": "string"
      +      },
      +      "upload_url": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "task_token"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "error": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "error"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedOutput schema / properties
      Removed value: -{
      -  "status_url": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "task_token": {
      -    "type": "string"
      -  },
      -  "upload_url": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  }
      -}
    • removedOutput schema / required
      Removed value: -[
      -  "task_token"
      -]
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare a destructive, non-idempotent, open-world write; the description adds substantial context beyond that: encoder_version is injected automatically (2 default, 1 when vmaf is present), a JSON-object payload triggers a retry-with-string error, only Media Storage destinations are accepted while credentials/presigned destinations are rejected, and specific outputs (advanced_hls bare form) are rejected outright. No contradiction with destructiveHint.

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 the one-line purpose, then structured by argument and output type; the length is justified by the composition traps it warns about. There is some redundancy — recipe lookup is mentioned twice and several examples repeat schema fragments — so it is dense rather than wasteful, but not perfectly trimmed.

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?

A high-complexity, three-parameter job-composition tool, and every decision an agent needs is present: valid output enums, nested stream[] placement, output-specific required fields, destination rules, and post-submission workflow. An output schema exists, so the description correctly does not spend words explaining the return payload.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden — and it does. It documents source URL schemes and the no-credentials rule, the critical `output` vs. `format` naming trap with a working example, per-output required fields (stream[] for HLS/DASH, distorted for vmaf, mode for video_intelligence), destination URL construction, and the exact payload semantics including what payload is not.

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?

Opens with a specific verb+resource ("Submit a transcoding job") and immediately scopes what that means for inputs and outputs. It also explicitly carves out the sibling case it does not cover (multi-source stitch → start_encode2_raw), so an agent can distinguish it without opening another schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use routing: fetch qencode://recipe/hls_abr (or audio_outputs) before composing ABR outputs, use start_encode2_raw for stitching, and consult recipes via search_qencode_docs + fetch_qencode_doc. It also prescribes the follow-up sequence — list_jobs with the returned task_token, then open_player or fetch_job_result depending on deliverable type.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.