How do I get my Descript API token?

Log in to your Descript account at **descript.com**. Navigate to **Settings** (click your profile icon). In the left sidebar, select **API tokens**. Click the **Create token** button, give it a descriptive name, and select the specific **Drive** you want it associated with. Copy the token immediately — it will **not** be shown again after you close the window. Paste it into the configuration field below.

Can I convert a podcast transcript into a blog post automatically?

Yes. Ask your AI agent to pull the full transcript from a Descript project, then instruct it to reformat the content into a structured blog post. It retrieves speaker labels, timestamps, and the complete text — perfect for creating show notes, summaries, or full articles from your recordings.

What if I work across multiple Descript drives?

Each API token is tied to a specific Drive. If you work across multiple drives (e.g., separate drives for different shows or clients), generate a separate token for each drive and configure multiple integrations. Your AI agent can then query projects from any of your drives.

Is this useful for agencies producing video content for clients?

Absolutely. Agencies can use the AI agent to pull transcripts across client projects, track export statuses, and retrieve download links — all from a single conversational interface. No need to log in and out of different client workspaces or manually download files from the Descript dashboard.

Descript MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Descript
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Descript through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Descript "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Descript?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Descript MCP Server

Connect Descript to your AI agent and manage your video and podcast production pipeline conversationally.

Pydantic AI validates every Descript tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Management — List, search, and retrieve project details including compositions, transcripts, and media files.
Transcript Access — Pull full transcriptions from any Descript project for repurposing into blog posts, social content, or subtitles.
Media Exports — Retrieve exported audio and video files, download links, and export statuses.
Drive Organization — Navigate your Descript drives and projects to find specific recordings or compositions.

The Descript MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Descript to Pydantic AI via MCP

Follow these steps to integrate the Descript MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Descript with type-safe schemas

Why Use Pydantic AI with the Descript MCP Server

Pydantic AI provides unique advantages when paired with Descript through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Descript integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Descript connection logic from agent behavior for testable, maintainable code

Descript + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Descript MCP Server delivers measurable value.

Type-safe data pipelines: query Descript with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Descript tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Descript and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Descript responses and write comprehensive agent tests

Descript MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Descript to Pydantic AI via MCP:

create_export

Export a project

create_transcription

Supports audio and video files. Transcribe a media file

get_project

Get project details

get_transcription

Get transcription result

list_drives

List team drives

list_exports

List project exports

list_projects

List all Descript projects

list_templates

List available templates

Example Prompts for Descript in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Descript immediately.

"List all my Descript projects."

"Get the full transcript of 'Podcast Ep 47'."

"Check if my latest video export is ready for download."

Troubleshooting Descript MCP Server with Pydantic AI

Common issues when connecting Descript to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Descript + Pydantic AI FAQ

Common questions about integrating Descript MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Descript MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.