How to Use the Descript MCP in CrewAI

Q: How does a CrewAI agent know when a Descript export is finished?

The agent runs a loop checking listexports until the status changes to completed. You can set this up as a sequential task where the next agent only starts once the export is ready.

Q: Does this server support multiple team drives in CrewAI?

Yes. Agents can invoke listdrives to discover all accessible workspaces, allowing them to organize and manage projects across your entire organization.

Run a crew of specialized CrewAI agents to manage your Descript library using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Descript MCP to CrewAI

Create your Vinkius account to connect Descript to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Descript with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy specialized CrewAI agents to manage Descript

The `list_projects` tool gives your CrewAI agents a complete view of all active video projects in your workspace over MCP. When a new video lands, the coordinator agent assigns the transcription task to a specialist. That specialist calls `create_transcription` and monitors the progress until the text is ready.

Run autonomous transcription review loops

The `get_transcription` tool lets your research agents pull raw text from finished media files for autonomous analysis. A second editor agent then reviews the text against your style guide. If changes are needed, they can coordinate to update the project details, ensuring your final exports are always polished.

Manage your rendering pipeline autonomously

The `create_export` tool allows your publishing agents to trigger video renders autonomously. A dedicated monitoring agent watches the queue by checking `list_exports` periodically. Once an export finishes, the agent can hand the final asset over to your publishing crew.

Setup guide

Set up Descript MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Descript tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Descript Analyst",
    goal="Access and analyze Descript data via MCP.",
    backstory="Expert analyst with direct Descript access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Descript transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Descript Analyst",
        goal="Access and analyze Descript data via MCP.",
        backstory="Expert analyst with direct Descript access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Descript transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Descript. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Descript now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Descript MCP in CrewAI

You can assign specific tools to different agents. For example, your manager agent uses `list_projects` to find files, while your editor agent uses `get_project` to analyze the contents.

Yes. When setting up the MCP Server connection in CrewAI, you can use a tool filter to only expose specific capabilities like `get_transcription` to your research agents.

The agent runs a loop checking `list_exports` until the status changes to completed. You can set this up as a sequential task where the next agent only starts once the export is ready.

Yes. Agents can invoke `list_drives` to discover all accessible workspaces, allowing them to organize and manage projects across your entire organization.

The MCP server processes all video files and project data locally within a secure sandbox. Your credentials and media assets are never exposed to external networks, keeping your proprietary content safe.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript