> 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.md). # AI & Agents - [Overview](https://docs.ilert.com/ai-and-agents/introduction.md): ilert AI brings intelligence and automation to your incident response process, from identifying related alerts and generating post-mortems to AI SRE agents that perform RCA autonomously - [AI Features](https://docs.ilert.com/ai-and-agents/ai-features.md): The AI features built into everyday ilert workflows, and how to turn the ones using external models off. - [AI global search](https://docs.ilert.com/ai-and-agents/ai-features/global-search-enhanced-by-ilert-ai.md): Access all resources in your ilert account easily. Search alerts, incidents, users, and alert sources. - [Bulk resolving similar alerts](https://docs.ilert.com/ai-and-agents/ai-features/global-search-enhanced-by-ilert-ai/bulk-resolving-similar-alerts.md): Bulk‑resolve similar alerts using ilert AI via global search to streamline cleanup and reduce alert handling time. - [Agents](https://docs.ilert.com/ai-and-agents/agents.md): What an agent is in ilert, and what the AI SRE and voice agents each do. - [AI SRE](https://docs.ilert.com/ai-and-agents/agents/sre-agent.md): Set up an AI SRE agent, connect the tools it reads from, and run your first root cause analysis. - [Alert triage](https://docs.ilert.com/ai-and-agents/agents/sre-agent/alert-triage.md): Ask your agent to cluster similar open alerts, so duplicates collapse into one parent alert instead of filling the list. - [MCP servers](https://docs.ilert.com/ai-and-agents/mcp.md): Agents get their tools from MCP servers — what they are, the two kinds, and how you attach one to an agent. - [ilert MCP server](https://docs.ilert.com/ai-and-agents/mcp/ilert-mcp-server-hosted.md): The official MCP endpoint for ilert, so an AI assistant can query and act on your alerts, incidents, services and schedules. - [ilert MCP connector](https://docs.ilert.com/ai-and-agents/mcp/ilert-mcp-connector.md): Deploy the read-only connector that lets ilert-hosted MCP servers reach Kafka, MySQL, PostgreSQL, ClickHouse and Redis inside your own network. - [Hosted by ilert](https://docs.ilert.com/ai-and-agents/mcp/hosted.md): The MCP servers ilert runs for you, and how ilert reaches systems that have no public endpoint. - [Clickhouse](https://docs.ilert.com/ai-and-agents/mcp/hosted/clickhouse.md): Give an agent read-only access to ClickHouse schemas and server metrics through the ilert MCP connector. - [GitHub](https://docs.ilert.com/ai-and-agents/mcp/hosted/github.md): Give an agent access to GitHub with a personal access token. - [Grafana](https://docs.ilert.com/ai-and-agents/mcp/hosted/grafana.md): Give an agent access to Grafana, Loki and Tempo with a service account token. - [Graylog](https://docs.ilert.com/ai-and-agents/mcp/hosted/graylog.md): Give an agent access to Graylog with an API token. - [Elasticsearch](https://docs.ilert.com/ai-and-agents/mcp/hosted/elasticsearch.md): Give an agent access to Elasticsearch with an API key scoped to the permissions it needs. - [InfluxDB](https://docs.ilert.com/ai-and-agents/mcp/hosted/influxdb.md): Give an agent access to InfluxDB with an API token. - [Kafka](https://docs.ilert.com/ai-and-agents/mcp/hosted/kafka.md): Give an agent access to Kafka through the ilert MCP connector you deploy in your own network. - [Kubernetes](https://docs.ilert.com/ai-and-agents/mcp/hosted/kubernetes.md): Give an agent access to a Kubernetes cluster by deploying ilert-kube-agent with Helm or Terraform. - [MySQL](https://docs.ilert.com/ai-and-agents/mcp/hosted/mysql.md): Give an agent read-only access to MySQL schemas and server metrics through the ilert MCP connector. - [Netdata](https://docs.ilert.com/ai-and-agents/mcp/hosted/netdata.md): Give an agent read-only access to Netdata Cloud with an API token. - [Prometheus](https://docs.ilert.com/ai-and-agents/mcp/hosted/prometheus.md): Give an agent access to Prometheus, using whichever authentication method your server has. - [Redis](https://docs.ilert.com/ai-and-agents/mcp/hosted/redis.md): Give an agent access to Redis through the ilert MCP connector, and the two gates on reading key values. - [ServiceNow](https://docs.ilert.com/ai-and-agents/mcp/hosted/servicenow.md): Give an agent access to ServiceNow with OAuth, and which of its tools write data as soon as they are called. - [External](https://docs.ilert.com/ai-and-agents/mcp/external.md): Connect an AI SRE agent to an MCP server you host yourself, over Streamable HTTP. - [AWS](https://docs.ilert.com/ai-and-agents/mcp/external/aws.md): Connect an agent to the AWS-hosted MCP server, which exposes AWS documentation and APIs. - [Datadog](https://docs.ilert.com/ai-and-agents/mcp/external/datadog.md): Connect an agent to Datadog's MCP server for metrics, logs, traces and monitors, using a bearer token. - [Dynatrace](https://docs.ilert.com/ai-and-agents/mcp/external/dynatrace.md): Connect an agent to a Dynatrace environment's MCP server for problems, logs, metrics and entity data. - [New Relic](https://docs.ilert.com/ai-and-agents/mcp/external/new-relic.md): Connect an agent to New Relic's MCP server for entities, NRQL queries, alerts and logs, using a User API key. - [Dash0](https://docs.ilert.com/ai-and-agents/mcp/external/dash0.md): Connect an agent to Dash0's MCP server for traces, metrics, logs and checks, using a bearer token. --- # 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.md?ask=&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.