3Scribe MCP. Transcribe any media, from video to podcast, with a single chat command.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
3Scribe. Automate transcription for audio and video. This server lets your AI client run the whole transcription lifecycle—from submitting a public URL to checking job status and getting the final text—all using natural language commands.
Forget manual data entry from media files; your agent handles the whole process.
What your AI agents can do
Create job
Starts a new transcription job by providing a public URL for audio or video.
Delete job
Permanently removes a transcription task and all data using a specific Job ID.
Get job
Checks the status of a job and retrieves the text transcript using the Job ID.
Submit a public URL for audio or video files, and 3Scribe starts processing the media and returns a Job ID.
Use the Job ID to check if a transcription is done and pull the final text output.
Retrieve a paginated list of every transcription job associated with your account.
Irrevocably delete a specific transcription task and all its associated data using the Job ID.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
3Scribe MCP Server: 4 Tools for Media Transcription
Use these four tools to manage the entire workflow: from starting a job with a URL to listing, checking, or deleting historical transcription tasks.
019d7541create job
Starts a new transcription job by providing a public URL for audio or video.
019d7541delete job
Permanently removes a transcription task and all data using a specific Job ID.
019d7541get job
Checks the status of a job and retrieves the text transcript using the Job ID.
019d7541list jobs
Gets a paginated list of all transcription tasks in your account.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with 3Scribe, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by 3Scribe. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 4 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Turning audio into text shouldn't feel like a full-time job.
Before 3Scribe, transcribing media was a multi-step mess. You'd download the file, upload it to a service, wait for a webhook, check a dashboard, and then copy-paste the resulting text into your document. It was a cycle of clicking, waiting, and manual data handling.
Now, your agent handles the whole thing. You give it the public URL, and it calls `create_job`. It then monitors the job status using `get_job`. The final text is ready in the chat. You just get the words, no manual steps required.
3Scribe MCP Server: Get structured transcripts in your chat.
The biggest time sink is the job lifecycle management. Before, you had to remember to check the job status manually and keep track of the Job ID across multiple tabs. Now, the agent handles that state tracking automatically.
It's simple. You start the job, and the agent knows how to follow up, check the status, and pull the final text. It keeps the conversation focused only on the result.
What you can do with this MCP connector
Your AI client handles the entire transcription process, from submitting a media link to getting the final text. You never gotta touch the 3Scribe dashboard yourself. Your agent acts like a direct pipeline to the recognition engine, handling everything from the initial media URL submission to pulling the finished text.
Using create_job, you'll start a new transcription job by giving it a public URL for either audio or video. This kicks off the processing and returns a Job ID.
With get_job, you check the status of a job using its Job ID and pull the final text transcript once it's done. You can also use this tool to check if the job is finished or if something went wrong.
If you need to know what's going on, list_jobs gives you a paginated list of every transcription job in your account.
When you're done with a job and want it gone for good, delete_job permanently removes that specific transcription task and all its associated data using the Job ID.
019d7544-f596-73e5-bc0d-2ce40d8a7103 
How 3Scribe MCP Works
- 1 Subscribe to the 3Scribe server and input your API Key.
- 2 Use your AI client to call
create_jobwith the public URL of the media file. - 3 Use
get_jobrepeatedly, passing the returned Job ID, until the status reports 'Completed', then retrieve the text.
The bottom line is: your AI agent handles the entire multi-step process, making the job look and feel like a single command.
Who Is 3Scribe MCP For?
Anyone whose job involves media content and text documentation. If you routinely handle podcasts, Zoom calls, interviews, or video footage, this saves you from tedious copy-pasting and manual transcription. It's for the person who needs to turn raw audio into searchable text, period.
Runs create_job on a YouTube video link, then uses get_job to pull captions for blog posts.
Submits multiple field recording URLs via create_job and tracks them all with list_jobs.
Converts long meeting recordings into structured text and uses get_job to pull speaker IDs for documentation.
Builds a media processing pipeline where create_job kicks off the task, and the agent monitors the results using get_job.
What Changes When You Connect
- Start a job instantly: Just provide the public URL to the audio or video file. The
create_jobtool handles the setup, and you get a Job ID right away. No manual form filling. - Know the status at a glance: Don't wait and wonder if the job worked. Use
get_jobto check the status (Requested, Processing, Completed) without needing to visit a web dashboard. - Get structured data: The text output isn't just plain text.
get_jobcan return detailed data, including timestamps and which speaker spoke the words. - Manage large volumes: Need to track dozens of files?
list_jobsgives you a paginated overview of every task, letting you manage your whole workload in one chat session. - Clean up data: Finished a project and want to clear out old records? Use
delete_jobto permanently wipe the data and keep your account clean.
Real-World Use Cases
Transcribing a multi-part podcast series
A content creator has 10 podcast episodes. Instead of uploading them one by one, they use their agent to run create_job on all 10 URLs sequentially. The agent then uses list_jobs to verify all jobs are in progress, and finally calls get_job for each one to gather all the transcripts.
Documenting a complex meeting
A technical writer records a 90-minute meeting. They ask their agent to run create_job on the recording link. Later, they use get_job to get the transcript, which includes speaker IDs, allowing them to draft accurate minutes for different participants.
Researching field recordings
A journalist records interviews from multiple locations. They run create_job on all the URLs. If a job fails, they can check the status with get_job and then use list_jobs to see which specific job failed, minimizing manual investigation time.
Cleaning up old media data
A developer finished a project and has hundreds of old job IDs. Instead of manually deleting them, they use list_jobs to pull a list of IDs, then instruct their agent to run delete_job on the whole batch.
The Tradeoffs
Trying to download media files
Thinking you need to download the audio file, process it locally, and then send it to the agent. This creates massive data transfer overhead and is slow.
→
Just send the public URL to the create_job tool. 3Scribe handles the file retrieval and processing internally. Your agent just needs the link.
Ignoring job status
Running create_job and then waiting hours without checking anything. You don't know if the job failed due to a bad URL or a server error.
→
Immediately use get_job with the returned Job ID. Your agent checks the status, and you'll know if you need to troubleshoot the URL or wait for completion.
Managing jobs one by one
Manually listing job IDs in a spreadsheet and calling the API for each one individually. This is slow and error-prone.
→
Use list_jobs to pull all active IDs into your chat, then use your agent to iterate through the list and run get_job on them all in one go.
When It Fits, When It Doesn't
Use 3Scribe if your core need is turning raw audio or video into structured, searchable text. The tools are built for the entire lifecycle: create_job starts it, list_jobs tracks the batch, get_job retrieves the final output, and delete_job cleans up. Don't use this if you just need to store the raw video files or analyze the video frames (that requires a different media processing service). If you only need to check status, get_job is enough, but you'll miss the ability to bulk-create jobs or view history with list_jobs.
Common Questions About 3Scribe MCP
How do I use the 3Scribe `create_job` tool? +
You must provide a valid, public URL for the audio or video. The tool accepts the link and immediately starts the transcription process, giving you a Job ID to track it.
What is the difference between `get_job` and `list_jobs`? +
get_job checks the status and text for one specific Job ID. list_jobs pulls a paginated list of all job IDs and their basic status.
How do I check if a job was successful using 3Scribe `get_job`? +
Run get_job with the Job ID. The status will tell you if it's 'Completed'. If it is, the tool also returns the actual transcribed text.
Can I delete all my old jobs using the 3Scribe `delete_job` tool? +
The delete_job tool only deletes a single job. You must first use list_jobs to get the IDs you want to delete, and then run delete_job for each ID.
Does 3Scribe support different languages? +
Yes. You can specify the transcription language when creating the job, or let the system automatically detect the language from the provided media URL.
What happens if I use the `create_job` tool with an invalid URL? +
The system returns an immediate error message stating the URL is invalid. This prevents starting a job and tells you exactly what needs fixing before you try again.
How do I handle the raw text and timestamps after running `get_job`? +
The output includes raw text and word-level data with timestamps and speaker IDs. You can process this structured data directly to build precise captions or speaker notes.
Can I filter the list of jobs using the `list_jobs` tool? +
Yes, list_jobs supports filtering by status. You can narrow down the results to only show 'Error' jobs or only 'Completed' jobs for quick cleanup.
How do I start a new transcription? +
Use the create_job tool and provide the public URL of your audio or video file. Your agent will initiate the process and provide a Job ID.
Can I check if a transcription is finished? +
Yes. Use the get_job tool with the Job ID. It will return the current status and, if completed, the transcribed text.
How can I clean up my transcription history? +
Use the delete_job tool and provide the Job ID. This permanently removes the transcription data from your 3Scribe account.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Hullo
Manage coworking spaces with desk bookings, member check-ins, and community engagement tools for modern workspaces.
CloudConvert
Convert files between 200+ formats including PDF, images, video, and documents with a fast cloud-based processing engine.
Monday.com
Manage any workflow visually with customizable boards, automations, and dashboards that adapt to how your team actually works.
You might also like
NPM Registry
Search and inspect the NPM registry — query package metadata, check versions, and explore the JavaScript ecosystem directly from your AI agent.
ManyChat
Automate messenger marketing via ManyChat — manage subscribers, tags, and flows directly from any AI agent.
Buffer
Plan, schedule, and publish social media content across all your channels with analytics that show what is working.