> 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.md).

# MCP servers

Agents get their tools from MCP servers — what they are, the two kinds, and how you attach one to an agent.

Agents get their abilities from **MCP servers**. An MCP server exposes a set of *tools* — read a log range, list Kubernetes pods, fetch a pull request diff — and an agent calls those tools while it works. Everything an agent can see or do outside ilert comes from an MCP server you connected.

There are two kinds:

<table><thead><tr><th width="196.734375">Kind</th><th>Who runs it</th><th>What you provide</th></tr></thead><tbody><tr><td><strong>ilert hosted</strong></td><td>ilert, inside its own infrastructure</td><td>A credential for your system (and, for some servers, a small component deployed in your network)</td></tr><tr><td><strong>External</strong></td><td>You, or the vendor of the tool</td><td>The server's public HTTPS URL plus the credential it expects</td></tr></tbody></table>

Both kinds are connected the same way: you create a connector once, then attach it to an agent on the agent's **Tools** tab and choose which of its tools the agent may use.

{% content-ref url="/pages/QINO4jIrPbW0wxTtIsfo" %}
[Hosted by ilert](/ai-and-agents/mcp/hosted.md)
{% endcontent-ref %}

{% content-ref url="/pages/CTQI2V3MRG8vq5QsyjHm" %}
[External](/ai-and-agents/mcp/external.md)
{% endcontent-ref %}

#### Related

* [AI SRE](/ai-and-agents/agents/sre-agent.md) — creating an agent and equipping it with tools
* [ilert MCP server (hosted)](/ai-and-agents/mcp/ilert-mcp-server-hosted.md) — the other direction: connecting your own LLM or IDE **to ilert** over MCP


---

# 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.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.