Compatible with every major AI agent and IDE
What is the Gotify MCP Server?
Connect your Gotify instance to any AI agent to streamline your notification workflows. Gotify is a self-hosted notification server, and this MCP server allows you to interact with its API using natural language.
What you can do
- Messaging — Send push notifications with custom priorities and titles, or retrieve and delete existing messages from your stream.
- Application Management — Create, list, update, or delete Gotify applications to organize your notification sources and tokens.
- Client Control — Manage clients and tokens to authorize different devices or services to receive messages.
- User Administration — (Admin only) List or create users to manage access to your private Gotify instance.
How it works
- Subscribe to this server
- Enter your Gotify URL and your Application or Client tokens
- Start sending alerts or managing your server from Claude, Cursor, or any MCP client
Who is this for?
- DevOps Engineers — automate alerts for CI/CD pipelines or server health checks directly from the terminal.
- Developers — test notification payloads and manage app tokens without leaving the code editor.
- Home Automation Enthusiasts — bridge your AI assistant with your self-hosted notification hub.
Built-in capabilities (22)
Change current user password
Create a new application
Create a new client
Create a new user (Admin only)
Delete all messages for the authenticated client
Delete an application
Delete a client
Delete a specific message
List all applications
List all clients
Get current user details
Get server health status
Requires GOTIFY_CLIENT_TOKEN. Retrieve messages
Get plugin configuration
Get plugin display info
List all plugins
List all users (Admin only)
Get server version info
Requires GOTIFY_APP_TOKEN. Send a message via Gotify
Update an application
Update a client
Update plugin configuration
Why Cursor?
Cursor's Agent mode turns Gotify into an in-editor superpower. Ask Cursor to generate code using live data from Gotify and it fetches, processes, and writes. all in a single agentic loop. 22 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Gotify in Cursor
Gotify and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Gotify to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Gotify in Cursor
The Gotify MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 22 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Gotify for Cursor
Every tool call from Cursor to the Gotify MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I send a notification to my phone using this server?
Use the send_message tool. You'll need to provide a message and a title. Ensure you have configured your GOTIFY_APP_TOKEN so the server knows which application is sending the alert.
Can I clear all messages from my Gotify stream at once?
Yes, you can use the delete_all_messages tool. This requires a valid GOTIFY_CLIENT_TOKEN to authorize the deletion of messages for that specific client.
Is it possible to create new application tokens via AI?
Absolutely. Use the create_application tool with a name and optional description. The AI will return the details of the new application, including its token.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Ontraport
10 toolsManage marketing and sales via Ontraport — list contacts, track campaigns, and monitor transactions directly from any AI agent.

EnterpriseAlumni
10 toolsEquip your AI agent to manage alumni networks, track engagement, and monitor member profiles via the EnterpriseAlumni API.

Bonusly
10 toolsRecognize and reward your team via Bonusly — give bonuses, track points, and view leaderboards directly from any AI agent.

Sendbird
18 toolsManage Sendbird chat infrastructure — orchestrate users, channels, and moderation directly from your AI agent.
