How to Use the Celigo integrator.io MCP in AutoGen

Q: How do I give my AutoGen agents access to Celigo integrator.io?

Install the autogen-extmcp package and use the mcpservertools function with your server URL. This returns a list of tools you can pass directly to your AssistantAgent during setup. The McpToolAdapter takes care of the rest.

Q: What's a use case for AutoGen and the Celigo integrator.io tools?

A team of agents for incident response. One agent using listintegrationerrors acts as a lookout. When it spots an error, it notifies another agent that can use getflowdetails to investigate, and a third that can propose a solution, like re-running a flow.

Q: How does the conversation between agents work?

One agent calls a tool, like listintegrationerrors, and posts the result to the group chat. Another agent reads that, decides the next step is to check connections, and calls listintegrationconnections. They continue this exchange until the problem is solved or they need human input.

Let multiple AutoGen agents debate and manage your Celigo integrator.io flows. Find the best solution through conversation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Celigo integrator.io MCP to AutoGen

Create your Vinkius account to connect Celigo integrator.io to AutoGen 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 Celigo integrator.io with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent DevOps for Celigo

This server provides the tools for a team of AutoGen agents to manage Celigo integrator.io. One agent, the "Monitor," can use `list_integration_errors` to spot problems. A second agent, the "Operator," can then use `run_integration_flow` to attempt a fix. The magic happens in the conversation. The Monitor might report an error, but the Operator could first use `get_flow_details` to check dependencies, then ask a human for confirmation before acting. This creates a safer, more deliberate automation system.

Build Consensus-Driven Actions

AutoGen's strength is debate. Imagine a "Security" agent that flags any new connections found via `list_integration_connections` as a potential risk. An "Engineering" agent could then cross-reference that with a list of approved services to validate it. The agents converge on a decision. Instead of one agent blindly acting, the group discusses the output from the MCP tools. This prevents rash actions and surfaces issues that a single agent might miss.

Integrate with your AutoGen Team

Adding these Celigo tools to your agent's skillset is direct. The `mcp_server_tools` function fetches the tools from the MCP Server, and the `McpToolAdapter` handles the schema conversion. Your `AssistantAgent` is ready to use them immediately. You can equip different agents with different subsets of tools. Give your monitoring agent read-only tools like `list_integrations`, but only give the trusted operator agent access to `run_integration_flow`. This enforces roles within your agent team.

Setup guide

Set up Celigo integrator.io MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Celigo integrator.io tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Celigo integrator.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Celigo integrator.io data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Celigo integrator.io_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Celigo integrator.io data")
    print(result.messages[-1].content)

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 Celigo integrator.io. 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 Celigo integrator.io 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 Celigo integrator.io MCP in AutoGen

Install the `autogen-ext[mcp]` package and use the `mcp_server_tools` function with your server URL. This returns a list of tools you can pass directly to your `AssistantAgent` during setup. The `McpToolAdapter` takes care of the rest.

Yes. You can fetch all the tools from the MCP server and then create separate lists for each agent. For example, create a `read_only_tools` list for a monitoring agent and a separate `action_tools` list with `run_integration_flow` for an execution agent.

A team of agents for incident response. One agent using `list_integration_errors` acts as a lookout. When it spots an error, it notifies another agent that can use `get_flow_details` to investigate, and a third that can propose a solution, like re-running a flow.

One agent calls a tool, like `list_integration_errors`, and posts the result to the group chat. Another agent reads that, decides the next step is to check connections, and calls `list_integration_connections`. They continue this exchange until the problem is solved or they need human input.

Yes. The agents only interact with metadata about your integrations—flow names, error logs, and connection settings. The underlying business data within your flows is not exposed. Each MCP Server session is isolated and secured by Vinkius's token-based authentication.

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