How to Use the autoRetouch MCP in CrewAI

Q: How does CrewAI handle failed autoRetouch executions?

If getexecution returns a failed status, the monitoring agent can analyze the error and instruct the editor agent to retry with a different workflow from listworkflows.

Deploy a team of specialized CrewAI agents to automate your autoRetouch image pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect autoRetouch MCP to CrewAI

Create your Vinkius account to connect autoRetouch 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 autoRetouch with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent coordination for bulk editing

Let specialized agents manage your catalog. A Librarian agent uses `list_images` and `list_workflows` to match new product shots with the correct editing templates. Once matched, an Editor agent calls `create_execution` to start the processing. They work in tandem, passing execution IDs back and forth without human handoffs.

Automated budget auditing via MCP Server

Prevent runaway costs with a dedicated Auditor agent. This agent checks `get_wallet_balance` before any major run and blocks executions if the budget is exceeded. The auditor can also monitor active runs using `get_execution` to ensure the cost per processed image matches your target metrics.

Sequential batch verification

Set up a strict pipeline where one agent triggers the edit and another verifies the output. The first agent initiates the job, while a second agent polls `get_batch` until it finishes. Once done, a third agent checks `get_image` to inspect the metadata and confirm the backgrounds were removed correctly before publishing.

Setup guide

Set up autoRetouch 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 autoRetouch tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the MCP server URL directly in your agent's mcps list. You can limit the Editor agent to create_execution while giving the Auditor agent access to get_wallet_balance.

Yes, you can set up a hierarchical crew where a manager agent oversees the entire pipeline. The manager calls list_executions to track active jobs and delegates verification tasks to subordinates.

If get_execution returns a failed status, the monitoring agent can analyze the error and instruct the editor agent to retry with a different workflow from list_workflows.

Use the MCPServerHTTP class from crewai.mcp for a stable, production-ready connection. This setup handles long-running image processing jobs without timing out during heavy batch runs.

This MCP Server processes all image files in an isolated environment. The crew only passes secure, temporary URLs to track progress, ensuring your master catalog assets remain protected and private.

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