How to Use the DeepAI MCP in CrewAI

Q: How do I assign DeepAI tools to specific CrewAI agents?

Use the MCPServerHTTP class from crewai.mcp along with a toolfilter. This lets you expose generateimage only to your designer agent while keeping other agents focused on text.

Run autonomous multi-agent creative teams using CrewAI and the DeepAI 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 DeepAI MCP to CrewAI

Create your Vinkius account to connect DeepAI 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 DeepAI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative multi-agent image generation

The `generate_image` tool outputs visual assets based on prompts crafted by your specialized research agents. Instead of a single agent doing everything, one agent writes the prompt while a designer agent invokes the tool. To set this up, pass the Vinkius URL directly into your CrewAI Agent configuration using the MCP parameter. The agents share memory, allowing a critic agent to review the output and ask for modifications.

Autonomous image editing with CrewAI agents

The `edit_image` tool applies targeted modifications to existing graphics based on feedback from other crew members. A supervisor agent can analyze an image, find flaws, and pass instructions directly to a designer agent to run the edit. You can use `MCPServerHTTP` from `crewai.mcp` to filter which agents have access to specific tools. This prevents your research agents from accidentally calling upscaling tools when they should only be writing text.

Multi-agent restoration pipelines

The `colorize_image` and `super_resolution` tools restore old, damaged, or low-resolution files through coordinated agent actions. A preservation agent first colorizes the black-and-white asset, then passes it to an upscaling agent to sharpen the details. CrewAI executes these steps sequentially or hierarchically depending on your crew's design. The entire process runs autonomously, outputting pristine, restored assets without any human intervention.

Setup guide

Set up DeepAI 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 DeepAI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Use the `MCPServerHTTP` class from `crewai.mcp` along with a `tool_filter`. This lets you expose `generate_image` only to your designer agent while keeping other agents focused on text.

Yes. CrewAI agents share memory, so an editor agent can review the output of `generate_image` and instruct a designer agent to call `edit_image` with specific correction prompts.

The simplest way is passing the Vinkius URL directly into the `mcps` array when defining your Agent. CrewAI handles the connection and tool discovery automatically.

CrewAI supports stdio, SSE, and Streamable HTTP transports. When hosted on Vinkius, the framework handles the HTTP connection details without requiring manual network configuration.

Yes. Your image files are transmitted over secure, encrypted TLS connections directly to isolated execution environments. Vinkius operates under a zero-trust model, meaning your data is never stored on disk or used for training.

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