_ registry / mcp streamable-http · checked 1h ago

cutconvert

https://cutconvert.com

Registry code: 5b33938056831af7

api record

CutConvert converts post-production files: subtitles (SRT, VTT, ASS, SBV, ITT, TTML), transcripts (Rev/Otter/Word TXT, Whisper JSON, Adobe Premiere .prtranscript), EDLs, FCPXML, CSV, and Word DOCX. Call list_converters to see every supported pair, then convert_file with the file content. Text files go in `content`; binary files (.prtranscript) go in `content_base64`. Anonymous usage has a small monthly free quota per IP. When a usage limit is reached, the tool explains the limit. To make an edit (clips, captions, titles) into projects for CapCut, Premiere Pro, DaVinci Resolve and Final Cut…

endpoint
https://cutconvert.com/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is cutconvert live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is cutconvert free to use?
Yes — the hub reached it with no key and no payment.
What tools does cutconvert have?
5 tools: convert_file, inspect_file, timecode_calculate, edit_export, list_converters.
Is cutconvert safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.8%

90 days 99.3%· all time 99.3%

latency
261ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 724 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
documents & files conversion
used for
  • convert subtitle files
  • convert transcripts between formats
  • detect subtitle file format
  • calculate smpte timecode
takes → gives
documents, text → documents, text
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
1 open 4 never probed 1 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_converters reads open 17h ago

    List every conversion CutConvert supports (source format, output format, and the target id to pass to convert_file).

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • convert_file reads unknown never probed

    Convert a subtitle, transcript, caption, EDL, FCPXML, or Premiere .prtranscript file. Pass text file contents in `content`; pass binary files (.prtranscript) as base64 in `content_base64`. The filename extension drives format detection. Use `target` from list_converters to pick the output, or leave it as "auto" to get the default output for the detected format. Returns the converted file content (text formats inline; DOCX/ZIP as base64).

    mcp-tool

    {
  "type": "object",
  "required": [
    "filename"
  ],
  "properties": {
    "target": {
      "enum": [
        "auto",
        "rppXml",
        "rppDrp",
        "rppFcpxml",
        "rppCapcut",
        "rppAaf",
        "prprojAaf",
        "fcpxmlAaf",
        "prprojRpp",
        "sesxRpp",
        "avbCsv",
        "avbXml",
        "avbFcpxml",
        "avbDrp",
        "avbAaf",
        "avbRpp",
        "avbShotlist",
        "avbEdl",
        "srtJson",
        "srtAvidTxt",
        "txtSrt",
        "edlCsv",
        "txtJson",
        "wordJson",
        "srtSbv",
        "srtAss",
        "srtVtt",
        "prtranscriptSrt",
        "prtranscriptVtt",
        "vttSrt",
        "srtText",
        "vttText",
        "prprojXml",
        "prprojDrp",
        "aafXml",
        "aafDrp",
        "fcpxmlXml",
        "fcpxmlDrp",
        "fcpxmlEdl",
        "fcpxmlShotlist",
        "drpXml",
        "prprojCsv",
        "prprojEdl",
        "prprojFcpxml",
        "drpFcpxml",
        "aafFcpxml",
        "drpCsv",
        "drpEdl",
        "aafCsv",
        "aafEdl",
        "prtranscriptDocx",
        "prtranscriptCsv",
        "capcutSrt",
        "capcutXml",
        "capcutDrp",
        "capcutFcpxml",
        "capcutAaf",
        "imovieCapcut",
        "imovieXml",
        "imovieDrp",
        "imovieFcpxml",
        "prprojCapcut",
        "drpCapcut",
        "fcpxmlCapcut",
        "aafCapcut",
        "filmoraXml",
        "filmoraDrp",
        "filmoraFcpxml",
        "filmoraAaf",
        "filmoraCapcut",
        "prprojFilmora",
        "drpFilmora",
        "fcpxmlFilmora",
        "aafFilmora",
        "capcutFilmora",
        "jsonVtt",
        "jsonDocx",
        "jsonText",
        "sccCsv",
        "mccCsv",
        "stlCsv",
        "fcpxmlDocx",
        "fcpxmlCsv",
        "prtranscriptText",
        "srtItt",
        "srtTtml",
        "sbvSrt",
        "srtDocx",
        "vttDocx",
        "assSrt",
        "jsonJson",
        "jsonSrt",
        "srtCsv",
        "csvSrt",
        "srtFcpxml",
        "fcpxmlSrt",
        "srtScc",
        "sccSrt",
        "srtMcc",
        "mccSrt",
        "srtStl",
        "stlSrt",
        "aafRpp",
        "fcpxmlRpp",
        "drpRpp",
        "drpAaf",
        "avbCapcut",
        "capcutRpp",
        "sesxXml",
        "sesxDrp",
        "sesxFcpxml",
        "sesxCapcut",
        "sesxAaf"
      ],
      "type": "string",
      "description": "Conversion target id from list_converters, or \"auto\" for the default output."
    },
    "content": {
      "type": "string",
      "description": "The file content for text formats (SRT, VTT, TXT, EDL, JSON, FCPXML, …)."
    },
    "filename": {
      "type": "string",
      "description": "Original file name including extension, e.g. \"episode1.srt\" — drives format detection."
    },
    "frame_rate": {
      "enum": [
        "auto",
        "23.976",
        "24",
        "25",
        "29.97",
        "30",
        "50",
        "59.94",
        "60"
      ],
      "type": "string",
      "description": "Frame rate for frame-based outputs such as ITT. Defaults to auto."
    },
    "content_base64": {
      "type": "string",
      "description": "Base64-encoded bytes for binary formats (.prtranscript)."
    },
    "caption_language": {
      "type": "string",
      "description": "BCP 47 caption language for ITT/TTML, e.g. en-US or ja. Defaults to the source language or undetermined."
    }
  },
  "additionalProperties": false
}
    arguments 159 lines
  • inspect_file reads unknown never probed

    Detect the format of a subtitle/transcript/EDL/FCPXML file and report what CutConvert would produce from it, without performing the conversion or using quota.

    mcp-tool

    {
  "type": "object",
  "required": [
    "filename"
  ],
  "properties": {
    "content": {
      "type": "string",
      "description": "File content (text formats)."
    },
    "filename": {
      "type": "string",
      "description": "Original file name including extension."
    },
    "content_base64": {
      "type": "string",
      "description": "Base64 bytes (binary formats like .prtranscript)."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • timecode_calculate reads unknown 17h ago

    Parse an SMPTE timecode at a frame rate (including 29.97/59.94 drop-frame) and report its frame count and real elapsed seconds; optionally re-express it at another rate.

    mcp-tool

    {
  "type": "object",
  "required": [
    "timecode",
    "rate"
  ],
  "properties": {
    "mode": {
      "enum": [
        "time",
        "frames"
      ],
      "type": "string",
      "description": "When converting rates: \"time\" keeps the same real-world moment (conform, default); \"frames\" keeps the frame count (reinterpret)."
    },
    "rate": {
      "enum": [
        "23.976",
        "24",
        "25",
        "29.97df",
        "29.97",
        "30",
        "50",
        "59.94df",
        "59.94",
        "60"
      ],
      "type": "string",
      "description": "Frame rate the timecode is expressed in."
    },
    "to_rate": {
      "enum": [
        "23.976",
        "24",
        "25",
        "29.97df",
        "29.97",
        "30",
        "50",
        "59.94df",
        "59.94",
        "60"
      ],
      "type": "string",
      "description": "Optional target frame rate to convert to."
    },
    "timecode": {
      "type": "string",
      "description": "Timecode like \"01:00:02:12\" (use \";\" before frames for drop-frame)."
    }
  },
  "additionalProperties": false
}
    arguments 54 lines
  • edit_export unknown never probed

    Turn an edit into projects that open in CapCut, Premiere Pro, DaVinci Resolve and Final Cut Pro, with captions and titles as each editor's own editable text. Pass a CutConvert Edit JSON document in `edit` and 1 to 4 editors in `targets`. Returns a zip as an embedded resource (application/zip): a folder for each editor and report.json, plus a short text with the warnings and the exports left. The tool sends no media. Each project points to the files at their `path` in the document; a file without a path opens offline, ready to relink. Each call is one export of the Edit API's allowance: 3 a month per network without a key, or an API key's 10 free a month and its packs when the MCP client sends "Authorization: Bearer cck_…". Edit JSON: times are seconds, positions are fractions of the frame, and unknown fields are errors. Every field: https://cutconvert.com/developers/edit-json (JSON Schema: https://cutconvert.com/developers/edit-json/schema.json). A small document: {"cutconvert":"edit/1","name":"My edit","timeline":{"fps":25,"width":1920,"height":1080},"media":[{"id":"a","name":"a.mp4","path":"/Users/sam/Movies/a.mp4","duration":30,"fps":25,"width":1920,"height":1080,"audio":{"streams":[2],"sampleRate":48000}}],"video":[{"clips":[{"media":"a","start":0,"in":2,"out":12}]}],"captions":{"items":[{"start":0.5,"end":3,"text":"Hello"}]}}

    mcp-tool

    {
  "type": "object",
  "required": [
    "edit",
    "targets"
  ],
  "properties": {
    "edit": {
      "anyOf": [
        {
          "type": "object"
        },
        {
          "type": "string"
        }
      ],
      "description": "The CutConvert Edit JSON document (version 1), as an object or as a string holding it. At most 8 MB."
    },
    "targets": {
      "type": "array",
      "items": {
        "enum": [
          "capcut",
          "premiere",
          "resolve",
          "finalcut"
        ],
        "type": "string"
      },
      "maxItems": 4,
      "minItems": 1,
      "description": "The editors to export for, each once: capcut (a CapCut desktop project folder), premiere (Premiere Pro XML), resolve (a DaVinci Resolve .drp project), finalcut (Final Cut Pro FCPXML).",
      "uniqueItems": true
    }
  },
  "additionalProperties": false
}
    arguments 37 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 5b33938056831af7.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/5b33938056831af7/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/5b33938056831af7/badge.svg)](https://brick.blue/agent/5b33938056831af7?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.