Supercharge your AI with 3Scribe. Turn any audio or video into searchable text.

Q: What should I use if I need to check the status of my transcription job?

You must use getjob. You'll supply the specific Job ID that was returned when you initially created the task. This tool checks the current state and pulls the text if done.

Q: Can I delete all my old jobs at once?

No, not directly. First, run listjobs to see what IDs exist. Then, you must call deletejob for each specific Job ID you want to permanently remove.

Q: If I run into an issue with a transcription, how does the getjob tool help me troubleshoot?

The getjob tool returns specific status codes and error messages when something goes wrong. If a job fails, you'll get details telling you if it was due to a bad URL or an internal processing fault.

Q: What format does the text output from getjob use for highly detailed data?

The raw text transcript retrieved by getjob includes rich metadata. You get timestamps for every segment, and it separates content using speaker IDs so you know exactly who said what.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

3Scribe: Automated transcription for audio and video files. This MCP lets your AI client manage the entire media processing lifecycle, from submitting a public URL to checking job status and retrieving text transcripts.

It handles everything needed for turning spoken word into structured, searchable data without manual intervention.

What your AI can do

Create job

Submits a public media URL to start the transcription process and returns a job ID.

List jobs

Gets a paginated list of all your current and past transcription tasks in the account.

Get job

Checks the status of a job ID and retrieves the full text transcript if processing is complete.

+ 1 more capabilities included

Initiate Transcription Jobs

Submit a public URL for an audio or video file to start the automated transcription process.

Track Job Status

Check if a job is pending, processing, completed, or failed using the assigned job ID.

Fetch Final Transcripts

Retrieve the full text transcript, including detailed timestamps and speaker identifications.

Manage Job Records

List all existing transcription jobs or permanently delete old job data to keep records clean.

Ask an AI about this

Compatible AI Apps

OAuth 2.0 Compatible

Claude

ChatGPT

Cursor

Gemini

VS Code

JetBrains

Vercel

Zendesk

+ any other MCP app

Included with Plan

Waiting for input…

AI Agent

3Scribe: Media Job Management (4 Tools)

These four tools allow you to manage the entire job lifecycle for media transcription tasks within the MCP.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using 3Scribe on Vinkius

Create Job

Submits a public media URL to start the transcription process and returns a job ID.

List Jobs

Gets a paginated list of all your current and past transcription tasks in the...

Get Job

Checks the status of a job ID and retrieves the full text transcript if processing...

Delete Job

Permanently removes a specific transcription task and all associated data from your...

Connect to your AI in seconds. Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The 3Scribe integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "3scribe": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the 3Scribe tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"3scribe": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

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

Start building

Make Your AI Do More

Start with 3Scribe, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ 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

Your data is protected. See how we built it.

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 connection provides 4 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manually transcribing media content is a massive time sink.

Think about it. A single hour of recorded meeting audio requires dedicated transcription work, which means listening, typing, and then proofreading the resulting text. You're constantly moving between the media player, the notes app, and the document where you paste chunks of text. It’s a repetitive, low-signal task that sucks up engineer time.

With this MCP connector, your agent handles the whole thing. You just pass the URL to the system, tell it what language to expect, and let it run in the background. The process moves from manual effort to a single command; you get clean, structured text data back without touching a keyboard.

3Scribe gives your agent complete control over media transcription jobs.

Before this, if you needed the transcript for three different projects, you'd have to run the process three times and manually track which job was finished. Now, you can use `list_jobs` to see all active projects in one place, giving you a single source of truth.

The difference is control. You aren't just submitting jobs; you are managing them as first-class resources. This means you can delete old records with `delete_job`, ensuring your data model stays clean and predictable.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Turning hours of recorded speech—whether it's meeting audio or video footage—into usable text used to be tedious. Now, your agent handles the whole process. You simply point your client at a media file URL and tell it what you need. The system takes care of creating the job, monitoring its progress in real time, and finally pulling out the raw transcript.

It’s like having a dedicated transcription service built right into your workflow. If you're building complex systems that deal with media data, connecting 3Scribe via Vinkius gives your agent access to this core functionality, making it easy for any compatible AI client to manage jobs and retrieve detailed word-level text.

Built · Hosted · Managed by Vinkius 3Scribe - Automated Audio/Video Transcription MCP

Server ID 019d7544-f596-73e5-bc0d-2ce40d8a7103

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

What Changes When You Connect

Stop manually transcribing. By calling create_job, your agent handles the media ingestion and job setup using just a public URL, saving hours of copy-paste work.

Get detailed data points, not just blocks of text. The system allows retrieval of word-level data with timestamps and speaker IDs via get_job for forensic accuracy.

Maintain clean records. Use list_jobs to see all your media tasks at a glance, and when you're done with an old project, use delete_job to wipe the record completely.

Flexible Language Handling. You can either specify the language type or let the system auto-detect the spoken language before initiating the job via create_job.

Workflow Automation. Instead of building a dedicated media API client, your agent handles this entire workflow using simple natural language commands across all four tools.

See it in action

01 01

Capturing Podcast Content

The marketing team needs captions for a new podcast episode. Instead of uploading files to a separate service, the agent uses create_job with the public URL and later calls get_job to pull the finalized transcript text for the website.

02 02

Auditing Old Records

A compliance officer needs to audit all historical meeting recordings. The agent first runs list_jobs to get a full manifest, then filters by status and deletes unnecessary projects using delete_job.

03 03

Analyzing Interview Data

A researcher records several interviews. They use create_job for each one. Later, they check the status of all jobs with get_job to ensure data is ready before pulling it into their database.

04 04

Batch Processing Media

A developer needs to process 50 video files simultaneously. They use list_jobs to track the progress of all submissions and can manually trigger checks on specific IDs using get_job until everything is marked 'Completed'.

The honest tradeoffs

Treating jobs like single files

Anti-pattern

Calling a series of separate APIs to check status, then another one to get the text, which leads to messy code and failure points.

The Fix

Manage the job lifecycle as a single resource. Use create_job first; once you get the Job ID, all subsequent actions—checking status or retrieving data—should reference that specific ID using get_job.

Forgetting to clean up

Anti-pattern

Leaving hundreds of old transcription jobs floating around that consume storage and complicate job listing views.

The Fix

After extracting the necessary data, proactively run delete_job for those completed tasks. You can find which ones need cleaning using list_jobs.

Assuming instant results

Anti-pattern

Calling get_job immediately after create_job and expecting the text, only to get an error because processing hasn't finished.

The Fix

Always check the status first. Use get_job repeatedly until the status is 'Completed'. The job ID you get from create_job is key here.

When It Fits, When It Doesn't

Use this MCP if your primary need is reliable, structured extraction of spoken word content from media files. If you are dealing with audio or video and need to manage the entire process—from submission to retrieval—this is for you. You must be comfortable managing a lifecycle: using create_job first, then polling status with get_job, and finally cleaning up with delete_job. Don't use this if your task is simple file conversion (e.g., MP4 to WAV) without the transcription requirement; use a dedicated media converter tool instead. Also, don't rely on it for real-time streaming captions; it handles batch jobs. This MCP provides explicit control over resource management, which means you get exactly what you need: granular tools like list_jobs and delete_job to manage the job database itself.

Questions you might have

How do I start a transcription job using the create_job tool? +

You provide the MCP with a valid public URL to the audio or video file. The system takes that URL, creates a unique Job ID for you, and starts processing it automatically.

What should I use if I need to check the status of my transcription job? +

You must use get_job. You'll supply the specific Job ID that was returned when you initially created the task. This tool checks the current state and pulls the text if done.

Can I delete all my old jobs at once? +

No, not directly. First, run list_jobs to see what IDs exist. Then, you must call delete_job for each specific Job ID you want to permanently remove.

Does the 3Scribe MCP handle video and audio? +

Yes, it handles both types of media equally well. The system accepts a public URL whether that file is an MP3 or an MP4, provided it's accessible.

If I run into an issue with a transcription, how does the `get_job` tool help me troubleshoot? +

The get_job tool returns specific status codes and error messages when something goes wrong. If a job fails, you'll get details telling you if it was due to a bad URL or an internal processing fault.

Does the `list_jobs` command allow me to filter tasks by their current processing status? +

Yes. The tool retrieves all jobs, but your agent can narrow down that list using filters. You can target specific statuses like 'Error' or 'Processing' without having to review every single record.

What format does the text output from `get_job` use for highly detailed data? +

The raw text transcript retrieved by get_job includes rich metadata. You get timestamps for every segment, and it separates content using speaker IDs so you know exactly who said what.

What happens if I try to run a job with an invalid public URL via the `create_job` tool? +

The system validates the provided public media URL before starting. If the link is inaccessible or improperly formatted, the agent will receive an immediate error notification, preventing any attempt to start a failed job.

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.

Connect to your AI in seconds.

Create job

List jobs

Get job

3Scribe: Media Job Management (4 Tools)

Make your AI actually useful.

Create Job

List Jobs

Get Job

Delete Job

Connect to your AI in seconds. Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Manually transcribing media content is a massive time sink.

3Scribe gives your agent complete control over media transcription jobs.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Capturing Podcast Content

Auditing Old Records

Analyzing Interview Data

Batch Processing Media

The honest tradeoffs

Treating jobs like single files

Forgetting to clean up

Assuming instant results

When It Fits, When It Doesn't

Questions you might have