> For the complete documentation index, see [llms.txt](https://docs.ilert.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ilert.com/ai-and-agents/mcp/ilert-mcp-server-hosted.md).

# ilert MCP server

The official MCP endpoint for ilert, so an AI assistant can query and act on your alerts, incidents, services and schedules.

The **ilert MCP Server** is the official [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) endpoint for ilert.\
It enables AI agents, coding assistants, and autonomous systems to **query, analyze, and act on your ilert resources** — including alerts, incidents, services, on-call schedules, and more.

***

### 🔗 Overview

* **Base URL:** `https://mcp.ilert.com/mcp`
* **Transport:** [Streamable HTTP](https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http)
* **Authentication:** API key (Bearer token)
* **Host:** ilert (no local installation required)

This hosted MCP server provides a secure, out-of-the-box connection for your AI assistants such as **Claude, Cursor, Cline, Windsurf**, or any MCP-compliant client.

***

### 🚀 Quick Installation

You can install and connect the ilert MCP server directly to a compatible AI assistant using the button below:

[![Install MCP Server](https://cursor.com/deeplink/mcp-install-light.svg)](https://cursor.com/en/install-mcp?name=ilert\&config=eyJ0eXBlIjoic3RyZWFtYWJsZUh0dHAiLCJ1cmwiOiJodHRwczovL21jcC5pbGVydC5jb20vbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyIHtZT1VSLUlMRVJULUFQSS1LRVktSEVSRX0ifX0%3D)

***

### 🔑 Authentication

The ilert MCP Server uses **API key authentication**.

1. Log in to your [ilert account](https://app.ilert.com/).
2. Go to **Profile → API Keys**.
3. Create a new API key for your user.
4. Copy the key and use it in the configuration examples below.

***

### ⚙️ Configuration Examples

#### Option 1 — Streamable HTTP (Preferred)

Use this configuration for clients that support **remote MCP servers** and **Streamable HTTP transport**:

```json
{
  "mcpServers": {
    "ilert": {
      "type": "streamableHttp",
      "url": "https://mcp.ilert.com/mcp",
      "headers": {
        "Authorization": "Bearer {{YOUR-API-KEY}}"
      }
    }
  }
}
```

This configuration works with most modern AI assistants such as **Cursor**, **Claude Desktop**, **Cline**, and **Windsurf**.

***

#### Option 2 — Using `mcp-remote` (Fallback)

For clients that do **not yet support Streamable HTTP**, you can use the [`mcp-remote`](https://www.npmjs.com/package/mcp-remote) CLI bridge:

```json
{
  "mcpServers": {
    "ilert": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.ilert.com/mcp",
        "--header",
        "Authorization: Bearer ${ILERT_AUTH_TOKEN}"
      ],
      "env": {
        "ILERT_AUTH_TOKEN": "{{YOUR-API-KEY}}"
      }
    }
  }
}
```

This configuration proxies the connection to the hosted ilert MCP endpoint via the local `mcp-remote` process.

***

### 🧠 What You Can Do with the ilert MCP Server

Once connected, your AI agent can:

* Retrieve and inspect **alerts**, **incidents**, and **on-call schedules**
* Analyze **alert timelines**, **incident communications**, and **root cause data**
* Correlate alerts with **deployment events**, **status pages**, or **GitHub commits**
* Automatically trigger **AI SRE investigations** within ilert

***

### 📚 Additional Resources

* [Model Context Protocol (MCP) Specification](https://modelcontextprotocol.io/introduction)
* [ilert Developer Documentation](https://app.gitbook.com/s/684bnaGsqSFjESghpiiu/README)
* [ilert AI & Automation Overview](/ai-and-agents/introduction.md)

***

### 🧩 Troubleshooting

| Issue                  | Possible Cause                             | Solution                                                                  |
| ---------------------- | ------------------------------------------ | ------------------------------------------------------------------------- |
| **401 Unauthorized**   | Missing or invalid API key                 | Verify that your API key is active and copied correctly.                  |
| **Connection refused** | MCP client doesn't support Streamable HTTP | Use the `mcp-remote` configuration instead.                               |
| **Empty responses**    | API key with limited scope                 | Ensure your key has sufficient permissions for alert and incident access. |

***

### 🛡️ Security Notes

* The MCP server **never stores** your API key — it's passed directly in the request header.
* The connection uses **HTTPS with Streamable HTTP** transport for secure, bidirectional communication.
* You can revoke API keys anytime from your [ilert user settings](https://app.ilert.com/profile/api-keys).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ilert.com/ai-and-agents/mcp/ilert-mcp-server-hosted.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.