How to Use the Castmagic MCP in CrewAI

Deploy autonomous CrewAI teams that extract, analyze, and repurpose Castmagic audio files without human input.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Castmagic MCP to CrewAI

Create your Vinkius account to connect Castmagic 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 Castmagic with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous MCP Server Content Crews

One agent writing a newsletter from a podcast is asking for mistakes. Connecting this MCP Server to CrewAI lets you build a specialized team where a Researcher agent pulls the raw text using `get_transcript_details`. That agent stores the data in shared memory for the rest of the crew to access. The Writer agent takes over next. It reads the shared memory, analyzes the context, and executes `get_magic_content` to fetch the AI-generated show notes. Because each agent has a specific role, the final output is significantly sharper than a single prompt trying to do everything at once.

Manage Speaker Attribution Automatically

Figuring out who said what in a panel discussion takes hours of manual review. You can assign an Editor agent to run `list_transcript_speakers` and map the names to the conversation. The agent cross-references the speaker tags with the raw text to ensure quotes are attributed correctly. If a speaker is missing, the crew can take corrective action. A Moderator agent watches the output, notices the discrepancy, and queries `list_castmagic_recordings` to verify the original file metadata. The team fixes its own errors before handing the final draft to you.

Monitor Quotas and Scrub Old Files

Hitting quota limits will crash an autonomous operation. You can build a dedicated Admin agent that fires `get_castmagic_account` at the start of every session. If the quota is dangerously low, it alerts you and pauses the crew before they attempt to process a massive video file. That same Admin agent handles routine maintenance. It can scan for stale projects using `list_transcripts` and execute `delete_transcript` to free up space. Your team manages the lifecycle of your media assets autonomously, keeping your account clean.

Setup guide

Set up Castmagic 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 Castmagic tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Castmagic 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="Castmagic Analyst",
        goal="Access and analyze Castmagic data via MCP.",
        backstory="Expert analyst with direct Castmagic access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Castmagic 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 Castmagic. 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 Castmagic 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 Castmagic MCP in CrewAI

Pass your Vinkius MCP Server endpoint URL directly into the `mcps` array when defining your agent. For more granular control, use `MCPServerHTTP` with a `tool_filter` to restrict which agent gets which specific tool.

Yes, they collaborate using shared memory. One agent can trigger `create_new_transcript` and save the ID, while a second agent waits for completion and pulls the text for analysis.

Use the tool filter feature in Python. Give your Admin agent access to `delete_transcript`, but restrict your Writer and Researcher agents to read-only actions like `get_magic_content`.

Set up a sequential execution flow. Have a dedicated uploader agent submit the media URL, verify the upload succeeds, and then pass the baton to the analysis crew.

Vinkius executes all requests in a zero-trust sandbox that never caches your media URLs, raw text, or speaker data. Your audio files and generated show notes are processed in memory and wiped immediately after the agent finishes its task.

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