How do I get an Access Token for Frame.io?

You can generate a Personal Access Token in the Frame.io Developer Portal at https://developer.frame.io.

Can I add comments with a specific timecode using the agent?

Yes! The 'add_comment' tool accepts an optional 'timestamp' parameter in seconds, allowing you to pin your feedback to a specific moment in the video.

How do I see the assets inside a specific folder?

Use the 'list_assets' tool and provide the Folder ID as the 'parentId'. The agent will return all files and sub-folders contained within that directory.

Is it possible to list external review links?

Yes! Use the 'list_review_links' tool and provide the Project ID. The agent will retrieve all active shared links for that project.

Frame.io MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Frame.io
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Frame.io through the 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 Frame.io "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Frame.io?"
    )
    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 Frame.io MCP Server

Connect your Frame.io account to any AI agent to automate your video collaboration and creative workflows through the Model Context Protocol (MCP). Frame.io is the industry-leading platform for reviewing and approving media, allowing teams to stay in sync from anywhere in the world. This MCP server enables you to manage your projects, retrieve asset metadata, and participate in time-coded discussions directly through natural conversation.

Pydantic AI validates every Frame.io tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the 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.

Key Features

Project Oversight — List all projects within your teams and fetch detailed metadata including ownership and status.
Asset Management — List files and folders within projects and retrieve complete metadata for specific media assets.
Collaborative Feedback — List all comments on an asset and add new time-coded feedback directly from your chat interface.
Review Coordination — Access and list review links to monitor how your media is being shared with external stakeholders.
Team Interaction — List team members and collaborators to maintain full context of who is involved in each project.
Directory Structure — Navigate through folders and sub-folders within your project library to organize your work effectively.
Real-time Monitoring — Fetch specific asset details or comments to keep your post-production workflow moving fast.

The Frame.io MCP Server exposes 12 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 Frame.io to Pydantic AI via MCP

Follow these steps to integrate the Frame.io 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 12 tools from Frame.io with type-safe schemas

Why Use Pydantic AI with the Frame.io MCP Server

Pydantic AI provides unique advantages when paired with Frame.io 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 Frame.io integration code

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

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

Frame.io + Pydantic AI Use Cases

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

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

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

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

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

Frame.io MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Frame.io to Pydantic AI via MCP:

add_comment

Post a new comment

get_asset_details

Get asset metadata

get_my_profile

Get current user profile

get_project_details

Get project metadata

list_accounts

List billing accounts

list_asset_comments

List comments on an asset

list_assets

List assets or folder contents

list_collaborators

List project collaborators

list_folders

List folders in project

list_projects

List projects in a team

list_review_links

List project review links

list_teams

List Frame.io teams

Example Prompts for Frame.io in Pydantic AI

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

"List all my projects in Frame.io team 'team_abc123'."

"Show me the last 5 comments on video asset 'vid_9876'."

"Add a comment to 'vid_9876': 'Great work, let\'s proceed to export' at 120 seconds."

Troubleshooting Frame.io MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Frame.io + Pydantic AI FAQ

Common questions about integrating Frame.io 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 Frame.io MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.