How to Use the Gotify MCP in CrewAI

Q: How do I pass Gotify MCP Server tools to a CrewAI agent?

You pass the server URL directly inside the agent's mcps array during initialization. CrewAI automatically discovers all tools, including getapplications and getclients.

Q: How do I restrict the MCP Server from deleting Gotify applications?

You can use a tool filter to only expose safe tools like sendmessage to your agents. This prevents them from calling destructive tools like deleteapplication.

Run specialized CrewAI agent teams using this MCP Server to manage Gotify notifications autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gotify MCP to CrewAI

Create your Vinkius account to connect Gotify 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 Gotify with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate team alerts using `send_message`

The `send_message` tool lets your CrewAI agents broadcast critical updates using this MCP Server. A researcher agent finds a system anomaly, and the coordinator agent uses this tool to dispatch an alert instantly. You assign specific Gotify application tokens to different agents based on their roles. This ensures your security agent sends high-priority alerts while your analytics agent logs lower-priority updates.

Audit Gotify users autonomously with CrewAI

The `get_users` tool allows your admin agent to audit the user list on your Gotify server. Our agent scans for unauthorized accounts and compares them against your internal staff database. If the agent detects a deactivated employee, it executes `create_user` or changes permissions to secure the server. The entire process runs in the background without human intervention.

Clean up notification queues programmatically

The `delete_all_messages` tool clears out old notification logs on your Gotify server to prevent database bloat. Your maintenance agent runs this tool on a schedule or when disk space runs low. By checking `get_health` first, the crew ensures the server is stable before running heavy cleanup routines. This keeps your self-hosted instance fast and responsive.

Setup guide

Set up Gotify 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 Gotify tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Yes, you can configure your CrewAI agents to set the priority parameter in `send_message`. A moderator agent can escalate critical alerts while ignoring minor system logs.

You pass the server URL directly inside the agent's `mcps` array during initialization. CrewAI automatically discovers all tools, including `get_applications` and `get_clients`.

Yes, they share access to the configured tools through the framework's memory system. One agent can fetch messages using `get_messages` while another sends an alert.

You can use a tool filter to only expose safe tools like `send_message` to your agents. This prevents them from calling destructive tools like `delete_application`.

All message text and admin credentials processed by tools like `create_user` stay within your local python runtime. CrewAI does not store or upload this private data to external cloud services.

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