FieldTranscript is an MCP server published by com.fieldtranscript, hosted at mcp.fieldtranscript.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including submit_transcription, get_job, list_jobs, delete_job.
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
1 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Submit a public video or audio URL (YouTube etc.) for verbatim transcription. Returns a job_id immediately. Transcription takes ~1-10 minutes: poll get_job with the job_id every 30-60 seconds until status is 'done', then call get_job with include_transcript=true. Not for private/internal URLs.
| Parameter | Type | Description |
|---|---|---|
| url * | string |
{
"name": "submit_transcription",
"description": "Submit a public video or audio URL (YouTube etc.) for verbatim transcription. Returns a job_id immediately. Transcription takes ~1-10 minutes: poll get_job with the job_id every 30-60 seconds until status is 'done', then call get_job with include_transcript=true. Not for private/internal URLs.",
"inputSchema": {
"type": "object",
"title": "submit_transcriptionArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Check a transcription job. Returns status (queued / working / done / error) and metadata. Set include_transcript=true only once status is 'done' and you actually need the full text in context - transcripts of long videos are large.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string | |
| include_transcript | boolean |
{
"name": "get_job",
"description": "Check a transcription job. Returns status (queued / working / done / error) and metadata. Set include_transcript=true only once status is 'done' and you actually need the full text in context - transcripts of long videos are large.",
"inputSchema": {
"type": "object",
"title": "get_jobArguments",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
},
"include_transcript": {
"type": "boolean",
"title": "Include Transcript",
"default": false
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}List all transcription jobs on your account, newest first.
No parameters.
{
"name": "list_jobs",
"description": "List all transcription jobs on your account, newest first.",
"inputSchema": {
"type": "object",
"title": "list_jobsArguments",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Permanently delete a finished (done or errored) transcription job and its stored text. Refused while the job is queued or running. This cannot be undone.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string |
{
"name": "delete_job",
"description": "Permanently delete a finished (done or errored) transcription job and its stored text. Refused while the job is queued or running. This cannot be undone.",
"inputSchema": {
"type": "object",
"title": "delete_jobArguments",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Verbatim transcription of videos and audio for LLM use. Submit a public video/audio URL, poll until done, then fetch the transcript. Jobs take roughly 1-10 minutes depending on length. Media is deleted from the server the moment the text is ready; only the text is kept.
Names, descriptions and schemas were written by the server and are shown as data.