How to Use the Descript MCP in Pydantic AI

Q: Can Pydantic AI list all Descript projects?

Use the listprojects tool to return a typed list of your assets. It integrates directly into your agent's state management.

Add type-safe Descript project management to your Pydantic AI agent.

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 Pydantic AI

Create your Vinkius account to connect Descript to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Descript tools for Pydantic AI

Every tool response is validated against a Pydantic model. If `get_project` returns malformed data, your agent catches it before it causes a runtime error. You get predictable behavior every time. It prevents silent failures when your agent interacts with project data.

Transcribe with Pydantic AI validation

The `create_transcription` tool provides structured outputs that your agent expects. You define the schema, and the server ensures the data matches your requirements. This eliminates hallucinated fields during transcription analysis. You rely on clean data for your logic gates.

Automate Descript exports in Pydantic AI

Use `list_templates` to find the right export format, then trigger `create_export` with validated parameters. The agent verifies the export state through `list_exports`. You create robust pipelines that handle media files programmatically. It works as an extension of your own typed Python code.

Setup guide

Set up Descript MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "descript-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Descript tools.",
)

result = await agent.run("List recent Descript transactions")
print(result.output)

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 Pydantic AI

Yes, use the MCPToolset to import the server tools. It validates every response against your Pydantic models at runtime for total reliability.

The server response is checked against your defined models. If the schema doesn't match, the agent throws an error immediately, stopping bad data flow.

Use the `list_projects` tool to return a typed list of your assets. It integrates directly into your agent's state management.

The MCP protocol communicates the error clearly. Because you are using Pydantic AI, you catch these exceptions in your standard try-except blocks.

Your media data is processed in a secure, ephemeral memory space. We never persist your project files or transcripts after the agent session closes.

Use it with your favorite AI tools

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

OpenAI Agents SDK sdk-python