YouTube Transcript — FlashData MCP server
Commit Nov 11, 2026Retrieve YouTube transcript text with start and end timestamps to build cited summaries and searchable notes.
Also known as rocosen/flashdata-mcp, youtube-transcript
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.2
- Last commit
- Nov 11, 2026
- License
- MIT
What is YouTube Transcript — FlashData MCP?
YouTube Transcript — FlashData retrieves YouTube transcript text with start and end timestamps to build cited summaries and searchable notes.
Summary generated from the project's README
About YouTube Transcript — FlashData MCP server
Extracting timestamped text from YouTube videos to create cited research notes is what this server enables. It allows developers to pull existing transcript segments, including start and end times, to build searchable databases or summaries. The tool works via a local stdio connection using Node.js 22.18 or newer and requires a FlashData API key with access to the youtube_transcript source.
Users interact with specific tools including youtube_transcript, get_pricing, get_job, and get_result. While the software installation is free, retrieving transcript data consumes paid FlashData Credits. The server handles both direct requests and asynchronous jobs, providing mechanisms to check job status or retrieve chunked results via offsets. It is designed for those who need to link specific text excerpts directly to video timestamps for accurate attribution.
What you can do with it
- 1Create timestamped research notesAsk the AI to extract English captions from a specific video and format them with timestamps and watch links.
- 2Monitor API credit usageCheck the current pricing and credit costs before executing a paid data request.
- 3Manage large transcript downloadsRetrieve long transcripts by processing multiple data chunks using result IDs and offsets.
- 4Track asynchronous data processingMonitor the status of a long-running transcript request using a job ID.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
FLASHDATA_API_KEYRequiredSecretYour FlashData API Key with youtube_transcript access. Get a key at https://flashdata.dev/app/api-keys; data calls are paid.
| Name | Description | |
|---|---|---|
| FLASHDATA_API_KEY | Your FlashData API Key with youtube_transcript access. Get a key at https://flashdata.dev/app/api-keys; data calls are paid. | RequiredSecret |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablerocosen/flashdata-mcp is public and reachablegithub.com/rocosen/flashdata-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-11github.com/rocosen/flashdata-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubYouTube Transcript — FlashData
Retrieve available YouTube transcript text with start and end timestamps. Build cited summaries, searchable notes and transcript exports.
API documentation and account setup · Get an API key · Current pricing
A task to try
Retrieve this video’s existing English automatic captions. Prepare timestamped excerpts and watch links for my research notes. Report an unavailable track without generating or translating a transcript.
Install and connect
- Use Node.js 22.18 or newer and an MCP client that supports local stdio servers. Download the dedicated MCPB package; its SHA-256 is recorded in the manifest.
- Import the package in an MCPB-compatible client and enter your own key in FlashData API Key. Grant the key access to
youtube_transcript. For manual setup, unpack the bundle into a permanent folder and use this configuration, replacing the absolute path and key placeholder:
{
"mcpServers": {
"youtube-transcript": {
"command": "node",
"args": [
"/absolute/path/to/unpacked/youtube-transcript/server.js"
],
"env": {
"FLASHDATA_API_KEY": "YOUR_API_KEY"
}
}
}
}
- Restart or reconnect the client, list its tools, then call
get_pricingwith{"source":"youtube_transcript","request_count":1}before approving a paid request. This server exposesyoutube_transcript,get_pricing,get_jobandget_result; all are restricted to this source.
Dependencies are included in the bundle. Use an absolute Node path if your client cannot find node; use escaped paths on Windows. Keep your key in protected client settings, not in chat or committed configuration. No Smithery account is needed for this direct package download.
Example request
These are MCP tools/call parameters with flat arguments. Running the data request uses paid Credits.
{
"name": "youtube_transcript",
"arguments": {
"video_id": "dQw4w9WgXcQ",
"language": "en",
"auto": true
}
}
Use the response
Read results[0].segments. Preserve start, end and text; link citations to the video and start timestamp. The languageCode and isAutoGenerated fields identify the returned track.
Selected response fields below are an illustrative fixture, not a live result or a guarantee of available data:
{
"source": "youtube_transcript",
"status": "done",
"results": [
{
"videoId": "dQw4w9WgXcQ",
"languageCode": "en",
"isAutoGenerated": true,
"segments": [
{
"start": 0,
"end": 3,
"text": "Example transcript."
}
]
}
],
"created_at": "2026-10-12T00:00:00Z",
"http_status": 200,
"request_id": "fixture-request"
}
For an asynchronous request, keep the returned id and call get_job with {"job_id":"RETURNED_JOB_ID"}. Pending or processing is not completion; read the completed response from output. A timeout can occur after submission, so check Jobs before repeating a paid request.
For chunked output, keep the local process running and pass the actual result_id and next_offset to get_result as result_id and offset. Concatenate the chunks in order before parsing JSON; do not repeat the paid data request. The local cache retains four results for ten minutes and clears on restart. Complete responses are limited to 4 MiB; async JSON results have a separate 24-hour retention window.
Cost and limits
- MIT software and installation are free; FlashData API data calls are paid. Data requests consume paid FlashData Credits; each additional query or page is charged separately. Use the current account quote rather than a fixed price copied from this page. Pricing, job and result reads are free. Client/model fees are separate.
- auto=true selects existing automatically generated captions; it does not run speech recognition. Missing tracks do not fall back to uploader captions or another language.
- Check API errors,
http_statusand job status before using the data. Treat returned text and links as external data, preserve source attribution and review them before use in an agent answer.
Full task guide · Official Registry record · Source and license
YouTube Transcript — FlashData MCP questions
Does this server generate new transcripts using speech recognition?
No, it retrieves existing automatically generated captions or uploaded tracks without running speech recognition.
Is using this server free?
The software and installation are free, but data requests consume paid FlashData Credits.
How can I check the status of an asynchronous request?
You should keep the returned job ID and call the get_job tool to check if the process is complete.
What should I do if a request times out?
You should check the Jobs before repeating a paid request to avoid duplicate charges.