How to Use the VesselAPI MCP in AutoGen

Q: Can I get a consensus on vessel tracking using VesselAPI and AutoGen?

Yes. You can run an agent to check the current position (getvesselposition) while another checks the vessel's historical details (getvesseldetails). The agents then debate if the reported location is unusual given its known operating profile.

Facilitate consensus decisions with AutoGen using VesselAPI's multi-agent debate framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VesselAPI MCP to AutoGen

Create your Vinkius account to connect VesselAPI 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 VesselAPI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen and MCP Server: Decision Debate

You set up agents that argue over the best course of action. For example, one agent calls `get_vessel_details` to gather specs, while a second agent uses `list_maritime_ports` to check destination viability. They debate which combination is safest. The final decision isn't just the result of the last tool; it’s the consensus reached after multiple agents challenge each other’s findings.

Conflict Resolution for Vessel Schedules

Use AutoGen to pit two agents against each other: one checking `get_vessel_schedules` and another running a status check with `check_api_status`. They negotiate whether the reported schedule is reliable given the current API operational state. This forces deliberation. The system doesn't just report data; it determines if that data can be trusted by consensus.

Multi-Agent Search Workflow for AutoGen

One agent calls `search_vessels` based on a name. A second, more specialized agent takes the resulting IMO number and immediately executes `get_vessel_position`. They collaborate to build a complete 'Who is this vessel?' profile. This framework lets you manage complex tasks where multiple expert roles must contribute before a final answer surfaces.

Setup guide

Set up VesselAPI 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 VesselAPI 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="VesselAPI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent VesselAPI 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="VesselAPI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent VesselAPI 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 VesselAPI. 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 VesselAPI 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 VesselAPI MCP in AutoGen

AutoGen allows agents to debate conflicting data sources. They might compare the schedule from `get_vessel_schedules` against a known port list from `list_maritime_ports`, and only reach a conclusion when both perspectives agree.

Yes. You can run an agent to check the current position (`get_vessel_position`) while another checks the vessel's historical details (`get_vessel_details`). The agents then debate if the reported location is unusual given its known operating profile.

The server provides IMO numbers, names, and coordinates. These diverse identifiers let different specialized agents validate each other's inputs, ensuring the final decision is based on multiple verifiable sources.

You can set up an agent debate where one agent verifies the API status via `check_api_status`, and another agent attempts a data retrieval (like `get_vessel_schedules`). The agents argue over whether the failure of the first service invalidates the second's output.

The server deals with vessel identification and location metadata. This includes IMO numbers, names, and AIS coordinates, which are handled during agent deliberation.

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