AI Agent Integration

Table of Contents

Prerequisites
Configuring the integration
Using the MCP tools

You can configure AI-based assistants that support the MCP SSE transport, such as Claude^[1] or OpenAI^[2], to interact in real time with MetricsHub's internal knowledge and tools.

OpenAI Prompt - MetricsHub MCP

The following tools are currently available:

Tool Name	Parameters	Description
`CheckProtocol`	`hostname` (list<string>, required) `protocol` (string, required) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Determines if the specified hosts are accessible using a given protocol. Supported protocols include: http, ipmi, jdbc, jmx, snmp, snmpv3, ssh, wbem, winrm, and wmi.
`CollectMetricsForHost`	`hostname` (list<string>, required) `connectorId` (string, optional) `poolSize` (integer, optional, default: 20 threads)	Fetch and collect metrics for the specified hosts using the configured protocols and credentials, and the applicable MetricsHub connectors (MIB2, Linux, Windows, Dell, RedFish, etc.)
`ExecuteHttpQueryService`	`url` (list<string>, required) `method` (string, optional, default: GET) `headers` (string, optional) `body` (string, optional) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Executes HTTP requests for one or more URLs and optionally includes custom headers, a request body, a timeout value, and concurrent execution settings. Except HTTP GET, all the other methods are disabled by default.
`ExecuteIpmiQueryService`	`hostname` (list<string>, required) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Executes an IPMI query on the given hosts with the given timeout.
`ExecuteSnmpQueryService`	`hostname` (list<string>, required) `queryType` (string, required) `oid` (string, required) `columns` (string, optional) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Executes an SNMP query (Get, GetNext, Walk, or Table) on the given hosts using the specified OID. For `table` queries, comma-separated column indexes need to be provided.
`ExecuteSshCommandlineService`	`hostname` (list<string>, required) `commandline` (string, required) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Executes the specified commandline through SSH on the given hosts. This service is disabled by default.
`ExecuteWqlQueryService`	`hostname` (list<string>, required) `protocol` (string, required) `query` (string, required) `namespace` (string, optional, default: root/cimv2 for WBEM and root\cimv2 otherwise) `timeout` (integer, optional, default: 10s) `poolSize` (integer, optional, default: 60 threads)	Executes a WQL/CIM query on Windows or WBEM-compatible hosts using the specified protocol (WBEM, WMI, or WinRM) and namespace.
`GetHostDetails`	`hostname` (list<string>, required) `poolSize` (integer, optional, default: 60 threads)	Fetch, for the given hosts, the configured protocols used to check their reachability, the connectors successfully detected as working, and the collectors available to perform requests on the hosts.
`GetMetricsFromCacheForHost`	`hostname` (list<string>, required) `poolSize` (integer, optional, default: 20 threads)	Retrieve metrics from the cache for the specified hosts
`ListConnectors`	No parameters.	Lists all connectors supported by MetricsHub including their identifiers and information.
`ListHosts`	No parameters.	Retrieves all configured hosts (Resources) in the MetricsHub Agent instance for which we will be able to execute MetricsHub connectors and collect metrics.
`PingHost`	`hostname` (list<string>, required) `timeout` (integer, optional, default: 4s) `poolSize` (integer, optional, default: 60 threads)	Checks if one or more hosts are reachable via ping and returns their response time and status.
`TestAvailableConnectorsForHost`	`hostname` (list<string>, required) `connectorId` (string, optional) `poolSize` (integer, optional, default: 20 threads)	Test all applicable MetricsHub connectors (MIB2, Linux, Windows, Dell, RedFish, etc.) against the specified hosts using the configured credentials and return the list of connectors that work with these hosts.

To get started, simply connect your AI assistant to the MetricsHub MCP Server using the Model Context Protocol (MCP)^[3]. Once the connection is established, the available tools will be automatically published and ready for use.

Prerequisites

Before configuring the AI agents integration, make sure that:

your AI assistant supports MCP SSE transport
MetricsHub is installed and running
you have network access to the machine where MetricsHub is running
the 31888 port is accessible from your machine or MCP client
you have generated an API key^[4] to authenticate against the MetricsHub MCP Server.

Important: Some MCP clients may require HTTPS with a valid TLS certificate. In such cases, you must enable HTTPS on your MetricsHub instance. One common approach is to place MetricsHub behind a reverse proxy (e.g., NGINX or Apache) with TLS termination, and ensure that the certificate is trusted by the client.

Configuring the integration

Configure your AI assistant to connect to http://<hostname>:31888/sse. Make sure to replace <hostname> with the actual hostname or IP address of the machine where MetricsHub is running.

Each request to the MetricsHub MCP Server must include the API key^[4] in the Authorization header as follows:

Authorization: Bearer <your_api_key>

Using the MCP tools

Once the connection is established, your AI assistant can call the PingHost tool as follows:

{
  "method": "tools/call",
  "params": {
    "name": "PingHost",
    "arguments": {
      "arg0": ["server-01", "server-02"]
    }
  }
}

The command will return this type of response:

{
  "hosts": [
    {
      "hostname": "server-01",
      "response": {
        "hostname": "server-01",
        "responseTime": 27,
        "reachable": true
      }
    },
    {
      "hostname": "server-02",
      "response": {
        "hostname": "server-02",
        "responseTime": 42,
        "reachable": false,
        "errorMessage": "Timed out"
      }
    }
  ]
}

Search Results for {{siteSearch | truncate:'50'}}

No results.

MetricsHub® MetricsHub Enterprise 3.0.02

AI Agent Integration

Prerequisites

Configuring the integration

Using the MCP tools

Search Results for {{siteSearch | truncate:'50'}}

MetricsHub®
MetricsHub Enterprise 3.0.02