How to Use the CaptionHub MCP in CrewAI

Q: How do I configure the CaptionHub MCP Server in CrewAI?

Run pip install crewai "crewaitools". For a basic setup, pass your managed URL directly into the mcps array on your Agent definition. The framework handles the connection automatically.

Q: Can I restrict CaptionHub tools to specific CrewAI agents?

Import MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give your manager agent access to project creation while restricting your reviewer agent to approval functions only.

Deploy autonomous localization teams with CrewAI and the CaptionHub MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CaptionHub MCP to CrewAI

Create your Vinkius account to connect CaptionHub 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 CaptionHub with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run localization teams with CrewAI

Managing global video releases requires coordination. You can assign one agent the role of Project Manager and another the role of Translator. The manager runs `list_projects` to find new uploads, while the translator executes `transcribe_video` to generate the initial text tracks. They share a unified memory space. When the translator finishes its job, the manager already knows the status. It pulls the latest data using `get_project_details` and updates the internal tracking systems without you writing any custom state management code.

Automate quality control and approvals

Hierarchical execution prevents mistakes. A junior agent generates the subtitles and runs `export_captions` to get a review link. A senior moderator agent reviews the text against brand guidelines. Only the senior agent holds permission to call `approve_captions`. You filter which tools each role can access. Using `MCPServerHTTP` with a `tool_filter`, you restrict the junior agent to read-only functions. The system enforces strict boundaries so a rogue prompt cannot accidentally approve a bad translation.

Handle workspace cleanup autonomously

Account maintenance wastes human hours. You can spin up a dedicated Janitor agent that runs on a weekly schedule. It checks your current limits with `get_account_info` and identifies stale campaigns. The cleanup process is entirely hands-off. The agent verifies the project status, checks active integrations via `list_webhooks`, and permanently deletes old files using `archive_project`. Your team logs in on Monday to a perfectly organized workspace.

Setup guide

Set up CaptionHub 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 CaptionHub tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Run `pip install crewai "crewai[tools]"`. For a basic setup, pass your managed URL directly into the `mcps` array on your Agent definition. The framework handles the connection automatically.

Import `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can give your manager agent access to project creation while restricting your reviewer agent to approval functions only.

The framework supports stdio, SSE, and Streamable HTTP transports. Your agents will wait for the initial API response and can be programmed to periodically check the status of a video job.

Agents share memory during sequential execution. If the first agent triggers a transcription, the downstream agents retain that context and know exactly which project ID to query for updates.

Your language tracks, export URLs, and account limits never touch public LLM training data. The MCP Server routes the framework's requests through an ephemeral isolation layer that drops the connection and destroys the sandbox after every single tool call.

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