> 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/hosted.md).

# Hosted by ilert

The MCP servers ilert runs for you, and how ilert reaches systems that have no public endpoint.

ilert runs these MCP servers for you. You do not deploy or update them — you only create a credential for the system the server talks to, and attach it to an agent. Each server has its own page below with the exact permissions it needs and the steps to connect it.

#### How ilert reaches your system

Most servers connect straight to an endpoint you already expose over HTTPS. Four of them read from systems that usually have no public endpoint at all, so they go through a small component you deploy in your own network.

<table><thead><tr><th width="243.15625">How it connects</th><th>Servers</th></tr></thead><tbody><tr><td>Directly to your HTTPS endpoint</td><td>Elasticsearch, GitHub, Grafana, Graylog, InfluxDB, Netdata, Prometheus, ServiceNow</td></tr><tr><td>Through <strong>ilert-mcp-connector</strong>, deployed by you</td><td>ClickHouse, Kafka, MySQL, Redis</td></tr><tr><td>Through <strong>ilert-kube-agent</strong>, deployed in your cluster</td><td>Kubernetes</td></tr></tbody></table>

{% hint style="info" %}
The connector and the kube agent exist so ilert never needs direct network access to a database, broker or cluster. You expose only the component, and it exposes only the read operations the MCP server uses.
{% endhint %}

One connector deployment serves ClickHouse, Kafka, MySQL and Redis together — deploy it once and enable the systems you need:

{% content-ref url="/pages/cKuRiKPs7NQX5toTeOJo" %}
[ilert MCP connector](/ai-and-agents/mcp/ilert-mcp-connector.md)
{% endcontent-ref %}

#### Connect a server

The flow is the same for every server on this page:

{% stepper %}
{% step %}
Create the credential the server needs — an API token, a service account, a database user. The server's page lists the exact permissions
{% endstep %}

{% step %}
Navigate to **Agents**, open your agent, and go to the **Tools** tab
{% endstep %}

{% step %}
Find the server under **ilert hosted MCP servers** and click **Connect**
{% endstep %}

{% step %}
Enter the credential and, where required, the **Host URL** of your system
{% endstep %}

{% step %}
Enable the tools the agent may use, then save the agent
{% endstep %}
{% endstepper %}

Connecting a server makes it available to that agent only. Other agents keep their own tool sets.

#### Available servers

<table><thead><tr><th width="180.1953125">Server</th><th>What the agent gets</th></tr></thead><tbody><tr><td><a href="/ai-and-agents/mcp/hosted/clickhouse.md">Clickhouse</a></td><td>Databases, tables, schemas and server metrics (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/elasticsearch.md">Elasticsearch</a></td><td>Indices, log searches and aggregations (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/github.md">GitHub</a></td><td>Pull requests and commit diffs (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/grafana.md">Grafana</a></td><td>Loki logs, dashboards and Tempo traces (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/graylog.md">Graylog</a></td><td>Streams and log searches (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/influxdb.md">InfluxDB</a></td><td>Measurements and time-series queries (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/kafka.md">Kafka</a></td><td>Topics, consumer groups and consumer lag (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/kubernetes.md">Kubernetes</a></td><td>Pod state, descriptions and logs — <strong>plus write tools</strong>: scale, patch CPU/memory, roll back, delete a pod</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/mysql.md">MySQL</a></td><td>Databases, tables, schemas and server metrics (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/netdata.md">Netdata</a></td><td>Rooms, nodes, alerts and metric queries (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/prometheus.md">Prometheus</a></td><td>Metric queries and series metadata (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/redis.md">Redis</a></td><td>Keyspace, key metadata and server metrics (read-only)</td></tr><tr><td><a href="/ai-and-agents/mcp/hosted/servicenow.md">ServiceNow</a></td><td>Records, incidents and cases — <strong>plus write tools</strong>: create, update and comment on incidents and cases</td></tr></tbody></table>

{% hint style="warning" %}
Only enable the tools an agent actually needs. The Kubernetes and ServiceNow servers include tools that change your systems, and every tool you enable is a tool the agent may decide to call.
{% endhint %}


---

# 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/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.