Server definition

Hash: sha256:4998afea55f08d3fa9ab2d72156e1cc0dfa86ff6021cefa8f2c8bb3910fb7ab3
What it is: What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{
  "instructions": "Subtitle Toolkit — convert, clean, retime and validate subtitle files (.srt, .vtt, .ass/.ssa, .sbv, .ttml/.dfxp).\n\nUse this server whenever the user provides or asks about subtitle/caption files: converting between formats,\ncleaning auto-generated captions, shifting or resyncing timing, checking reading speed and cue durations,\nmerging or splitting tracks, repairing mojibake, or turning a plain transcript into timed cues.\n\nDo NOT hand-write a subtitle parser for these tasks. These tools already handle the cases ad-hoc code gets wrong:\nASS/SSA field order declared by a Format: line, TTML clock vs offset vs frame vs tick time values,\nSBV timestamps, centisecond vs millisecond precision, and cp1252/cp1251 mojibake repair.\n\nWorkflow: pass the file text as `content`. Use `from: \"auto\"` unless you know the format.\nFor timing fixes, prefer `offset_seconds` when the whole track is uniformly early/late, and `ratio`\nor `from_fps`/`to_fps` when the drift grows over time (a frame-rate mismatch).",
  "tools": [
    {
      "description": "Audit subtitle readability and produce a report: reading speed (CPS), cue durations that are too short or too long, lines that are too wide, more than two lines, and overlapping cues. Returns a formatted report listing every flagged cue.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The full subtitle file text.",
            "type": "string"
          },
          "max_cps": {
            "description": "Max characters per second. Default 20.",
            "type": "number"
          },
          "max_duration_seconds": {
            "description": "Maximum cue duration in seconds. Default 7.",
            "type": "number"
          },
          "max_line_length": {
            "description": "Max characters per line. Default 42.",
            "type": "number"
          },
          "min_duration_seconds": {
            "description": "Minimum cue duration in seconds. Default 0.833 (Netflix 5/6s).",
            "type": "number"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "check_subtitle_timing",
      "outputSchema": null
    },
    {
      "description": "Strip noise from auto-generated subtitles: HTML/WebVTT tags, ASS override codes, music and sound-effect cues, speaker labels, empty cues and duplicate lines. Returns the subtitle file in SRT or WebVTT.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The full subtitle file text.",
            "type": "string"
          },
          "drop_duplicates": {
            "description": "Drop cues whose text was already seen. Default false.",
            "type": "boolean"
          },
          "drop_empty": {
            "description": "Drop cues that become empty after cleaning. Default true.",
            "type": "boolean"
          },
          "remove_sound_cues": {
            "description": "Strip [Music], [Applause], ♪ ... ♪ and similar. Default true.",
            "type": "boolean"
          },
          "remove_speaker_labels": {
            "description": "Strip leading \"SPEAKER:\" prefixes. Default false — enable only if you want them gone.",
            "type": "boolean"
          },
          "remove_tags": {
            "description": "Strip HTML/WebVTT tags and ASS override codes. Default true.",
            "type": "boolean"
          },
          "to": {
            "description": "Output format. Default: same as the input.",
            "enum": [
              "srt",
              "vtt"
            ],
            "type": "string"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "clean_subtitles",
      "outputSchema": null
    },
    {
      "description": "Convert subtitle text between formats. Reads SRT, WebVTT, ASS/SSA, YouTube SBV and TTML/DFXP; writes SRT, WebVTT, ASS, CSV or plain text. Format is auto-detected unless `from` is given.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The full subtitle file text.",
            "type": "string"
          },
          "dedupe": {
            "description": "Only for to=\"text\": collapse consecutive identical lines (rolling-caption transcripts repeat lines). Default false.",
            "type": "boolean"
          },
          "from": {
            "description": "Source format (default \"auto\" = detect).",
            "enum": [
              "auto",
              "srt",
              "vtt",
              "ass",
              "sbv",
              "ttml"
            ],
            "type": "string"
          },
          "to": {
            "description": "Target format. `text` = plain transcript, one line per cue, no timecodes.",
            "enum": [
              "srt",
              "vtt",
              "ass",
              "csv",
              "text"
            ],
            "type": "string"
          }
        },
        "required": [
          "content",
          "to"
        ],
        "type": "object"
      },
      "name": "convert_subtitle",
      "outputSchema": null
    },
    {
      "description": "Repair mojibake — text where UTF-8 bytes were decoded as a single-byte encoding (cp1252/Latin-1 or cp1251). Symptoms: \"Ã©\", \"â€™\", \"Ð¿Ñ€Ð¸Ð²ÐµÑ‚\". Returns the repaired text and how many passes were applied.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The garbled subtitle text.",
            "type": "string"
          },
          "read_as": {
            "description": "Which encoding the file was wrongly read as. Default \"auto\" (tries cp1252 then cp1251).",
            "enum": [
              "auto",
              "cp1252",
              "cp1251"
            ],
            "type": "string"
          },
          "twice": {
            "description": "Set true when the text was mis-decoded twice (nested mojibake). Default false.",
            "type": "boolean"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "fix_subtitle_encoding",
      "outputSchema": null
    },
    {
      "description": "Append one subtitle track after another (CD1 + CD2, or a second language track). The second track is offset so it starts after the last cue of the first, plus an optional gap.",
      "inputSchema": {
        "properties": {
          "append_content": {
            "description": "The subtitle file text to append.",
            "type": "string"
          },
          "content": {
            "description": "The first subtitle file text.",
            "type": "string"
          },
          "gap_seconds": {
            "description": "Extra gap between the two tracks, in seconds. Default 0.",
            "type": "number"
          },
          "to": {
            "description": "Output format. Default: same as the input.",
            "enum": [
              "srt",
              "vtt"
            ],
            "type": "string"
          }
        },
        "required": [
          "content",
          "append_content"
        ],
        "type": "object"
      },
      "name": "merge_subtitles",
      "outputSchema": null
    },
    {
      "description": "Fix subtitle timing. Use offset_seconds for a uniform shift (whole track early/late). Use ratio, or from_fps/to_fps, for progressive drift caused by a frame-rate mismatch. Pass exactly one of the three.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "The full subtitle file text.",
            "type": "string"
          },
          "from_fps": {
            "description": "The frame rate the subtitles were authored for (used with to_fps).",
            "type": "number"
          },
          "offset_seconds": {
            "description": "Shift every cue by this many seconds. Negative = earlier. e.g. -2.5",
            "type": "number"
          },
          "ratio": {
            "description": "Scale all timings by this factor (new = old x ratio). e.g. 1.0427 for a 25→23.976 fps fix.",
            "type": "number"
          },
          "to_fps": {
            "description": "The frame rate of the actual video (used with from_fps).",
            "type": "number"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "retime_subtitles",
      "outputSchema": null
    },
    {
      "description": "Split one subtitle track into two parts at a given timecode, keeping original timecodes. Use the `at` argument plus `part` to fetch either half.",
      "inputSchema": {
        "properties": {
          "at": {
            "description": "Split point. Accepts \"45:00\", \"1:02:03\", \"90\" (seconds) or \"1:02:03.500\".",
            "type": "string"
          },
          "content": {
            "description": "The full subtitle file text.",
            "type": "string"
          },
          "part": {
            "description": "Which half to return. Default \"a\" (before the split point).",
            "enum": [
              "a",
              "b"
            ],
            "type": "string"
          },
          "to": {
            "description": "Output format. Default: same as the input.",
            "enum": [
              "srt",
              "vtt"
            ],
            "type": "string"
          }
        },
        "required": [
          "content",
          "at"
        ],
        "type": "object"
      },
      "name": "split_subtitles",
      "outputSchema": null
    },
    {
      "description": "Turn a plain transcript (one line per caption) into an SRT file with evenly spaced timecodes. Timing is a starting point, not a real transcription — say so when you present the result.",
      "inputSchema": {
        "properties": {
          "content": {
            "description": "Plain text, one caption per line. Blank lines are skipped.",
            "type": "string"
          },
          "duration_seconds": {
            "description": "Seconds each cue stays on screen. Default 2.5.",
            "type": "number"
          },
          "max_chars_per_cue": {
            "description": "Split longer lines into several cues at word boundaries. Default 0 = never split.",
            "type": "number"
          },
          "start_seconds": {
            "description": "Timecode of the first cue, in seconds. Default 0.",
            "type": "number"
          }
        },
        "required": [
          "content"
        ],
        "type": "object"
      },
      "name": "text_to_subtitles",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:4998afea55f08d3fa9ab2d72156e1cc0dfa86ff6021cefa8f2c8bb3910fb7ab3 | sha256sum