How to Use the Spiritme MCP in CrewAI

Q: What if I need to change the message after the initial video run with Spiritme and CrewAI?

You can use generateaudio to create the updated track, then delete the old version using deletevideo, and finally re-run generatevideo with the new components.

Q: If I need a complete audit of all assets used by Spiritme and CrewAI, what should I check?

You'll want to cross-reference calls to listvideos, listtemplates, and the logs from job status checks. This gives you a full history of every asset ID.

Run autonomous marketing operations using Spiritme with CrewAI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spiritme MCP to CrewAI

Create your Vinkius account to connect Spiritme to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Spiritme with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Autonomous Video Campaign Management via MCP Server

A crew of specialized agents can manage a full campaign cycle. Agent A uses `list_templates` to research available layouts, while Agent B uses `get_avatar` to select the right presenter for the message. Then, Agent C takes over, calling `generate_video`. The system handles this sequential execution and keeps track of all assets created.

Multi-Step Content Creation with Spiritme

You can set up a hierarchical workflow: first, call `get_voice` to confirm the necessary speech parameters. Second, use `generate_audio` to create the core message track. Third, pass both assets into `generate_video`. This process simulates how human teams work—breaking down a large task into smaller, dependent steps that must run in order.

Monitoring and Reporting with the MCP Server

One agent monitors the entire operation by repeatedly calling `get_job_status`. This prevents any single failure from stopping the whole campaign. Another agent can use `list_videos` to compile a final report. This shared memory capability means all agents are working off the same, current list of assets and job statuses.

Setup guide

Set up Spiritme 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 Spiritme tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

CrewAI treats the MCP Server tools as specialized skills for its agents. An agent doesn't just call a function; it decides *when* and *why* to use `generate_video` based on the overall campaign goal.

The system handles template structures, voice metadata, avatar details, job status reports, and the final video file references. The agents work off this rich pool of structured information.

Yes, an agent can be assigned the task of checking job status by calling `get_job_status` in a loop. This gives you real-time visibility into every running asset.

You can use `generate_audio` to create the updated track, then delete the old version using `delete_video`, and finally re-run `generate_video` with the new components.

You'll want to cross-reference calls to `list_videos`, `list_templates`, and the logs from job status checks. This gives you a full history of every asset ID.

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