How to Use the NavAPI MCP in CrewAI

Q: Can I have one CrewAI agent find routes with NavAPI and another agent analyze them?

Yes, that's a primary use case. The first agent would call searchmaritimeroutes and pass the output to the second agent. The second agent could then use tools like getportdistance to perform its analysis.

Deploy autonomous agent crews with CrewAI to monitor, analyze, and act on live maritime data from the NavAPI server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NavAPI MCP to CrewAI

Create your Vinkius account to connect NavAPI 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 NavAPI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Autonomous Port Watcher Crew

Assign roles to a team of agents for 24/7 monitoring. A 'Scout' agent can run `get_nautical_ports` to define a territory. A 'Watcher' agent then periodically calls `get_port_vessel_traffic` for each port in that territory. If traffic at any port exceeds a defined threshold, the Watcher passes the alert to a 'Reporter' agent, which can then take action. This is how you build a hands-off monitoring system using this MCP server and a specialized crew.

Create a Route Analysis Team

Use a multi-agent workflow to find the best shipping routes. First, a 'Researcher' agent calls `search_maritime_routes` to generate several potential options. It passes those options to an 'Analyst' agent. The Analyst agent then uses `get_port_distance` to compare their lengths and `list_nautical_charts` to check for potential hazards. This division of labor lets each agent focus on one part of the problem, leading to a better, more thoroughly vetted result.

Automate Maritime Safety Audits

Deploy a crew dedicated to ensuring compliance and safety. You can have one agent whose only job is to check `check_api_status` to ensure the system is online. Another agent could be responsible for using `list_nautical_charts` to verify that all planned routes are using up-to-date chart versions. This kind of role-based specialization is exactly what CrewAI is for. You can build a truly autonomous operation where different agents handle monitoring, execution, and verification for all your maritime tasks.

Setup guide

Set up NavAPI 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 NavAPI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass your Vinkius URL directly into the `mcps` list when defining an Agent. For more control, you can use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter` to expose specific tools to specific agents.

Yes, that's a primary use case. The first agent would call `search_maritime_routes` and pass the output to the second agent. The second agent could then use tools like `get_port_distance` to perform its analysis.

You would assign one agent the task of periodically calling `get_port_vessel_traffic` for a list of critical ports. If the traffic numbers cross a threshold you set, that agent's task output would trigger another agent in the crew to take action.

Yes. You can use the NavAPI tools within both sequential and hierarchical crews. The tools are stateless, so they work just as well for a simple task sequence as they do for a complex, multi-layered agent delegation process.

Each agent's call for maritime data is an independent transaction. The Vinkius MCP server receives a request for port, route, or traffic data, processes it in an isolated environment, and returns the result. The server has no awareness of your agent's role or the crew's larger mission, and it doesn't log the data.

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