Skip to main content

Model Context Protocol (MCP)

Unizo offers an MCP server that integrates observability platforms with any LLM provider supporting the MCP protocol. This enables your AI agent to analyze logs, metrics, and traces, investigate issues, and automate monitoring workflows across Datadog, New Relic, Splunk, and other observability tools via a single MCP server.

Supported Tools & Use Cases​

The following tools are available in the Observability MCP Server:

Tool NameDescription
list_servicesGet list of available observability services
list_integrationsGet integrations for a specific observability service
list_logsBrowse and search logs with advanced filtering and pagination
get_log_detailsRetrieve comprehensive log entry information

list_services​

Get list of available observability services

Parameters: None

Returns: List of available observability services

Example Response:

[
  { "name": "elasticsearch" },
  { "name": "splunk" },
  { "name": "datadog" },
  { "name": "newrelic" },
  { "name": "prometheus" }
]

list_integrations​

Get integrations for a specific observability service

Parameters:

  • service (string, required): Name of the observability service (e.g., "elasticsearch", "splunk", "datadog")

Returns: List of integrations available for the specified service

Example Response:

[
  {
    "id": "integration-obs-123",
    "name": "Production Logging Integration"
  },
  {
    "id": "integration-obs-456",
    "name": "Development Environment Logs"
  }
]

list_logs​

Browse and search logs with advanced filtering and pagination options

Parameters:

  • integration_id (string, required): Unique identifier for the integration
  • offset (integer, optional): Number of records to skip for pagination (default: 0)
  • limit (integer, optional): Maximum number of records to return (default: 20, max: 100)
  • sort (string, optional): Field to sort by, prefixed with '-' for descending order
    • Valid sort fields: timestamp, level, source, message
    • Examples: -timestamp (newest first), level (ascending), -level (severity order)

Returns: Paginated list of log entries with filtering applied

Example Response:

{
  "status": "success",
  "message": "Retrieved 25 logs",
  "data": {
    "logs": [
      {
        "id": "log-2024-09-10-14-30-15-abc123",
        "level": "ERROR",
        "message": "Failed to process payment transaction: Connection timeout after 30s",
        "source": "payment-service",
        "timestamp": "2024-09-10T14:30:15Z",
        "metadata": {
          "service": "payment-service",
          "environment": "production",
          "region": "us-east-1",
          "traceId": "00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01",
          "spanId": "b7ad6b7169203331",
          "hostname": "payment-service-01",
          "version": "1.2.3",
          "tags": ["payment", "transaction", "timeout"]
        },
        "changeLog": {
          "createdDateTime": "2024-09-10T14:30:15Z",
          "createdBy": {
            "id": "system",
            "firstName": "System",
            "lastName": "Logger"
          }
        }
      },
      {
        "id": "log-2024-09-10-14-29-45-def456",
        "level": "INFO",
        "message": "User authentication successful for user ID: 12345",
        "source": "auth-service",
        "timestamp": "2024-09-10T14:29:45Z",
        "metadata": {
          "service": "auth-service",
          "environment": "production",
          "region": "us-east-1",
          "traceId": "00-1bf8762827de54ff9559ab302d91827f-c8e4586412b53462-01",
          "spanId": "c8e4586412b53462",
          "hostname": "auth-service-02",
          "version": "2.1.0",
          "tags": ["authentication", "success", "user"]
        }
      }
    ],
    "pagination": {
      "total": 1250,
      "offset": 0,
      "limit": 20,
      "next": 20
    },
    "total_count": 1250
  }
}

get_log_details​

Get detailed information about a specific log entry

Parameters:

  • integration_id (string, required): Unique identifier for the integration
  • log_id (string, required): Unique identifier of the log entry

Returns: Comprehensive log entry information including all metadata

Example Response:

{
  "status": "success",
  "message": "Retrieved log details for log-2024-09-10-14-30-15-abc123",
  "data": {
    "log": {
      "id": "log-2024-09-10-14-30-15-abc123",
      "level": "ERROR",
      "message": "Failed to process payment transaction: Connection timeout after 30s",
      "source": "payment-service",
      "timestamp": "2024-09-10T14:30:15Z",
      "metadata": {
        "service": "payment-service",
        "environment": "production",
        "region": "us-east-1",
        "traceId": "00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01",
        "spanId": "b7ad6b7169203331",
        "hostname": "payment-service-01",
        "version": "1.2.3",
        "tags": ["payment", "transaction", "timeout"]
      },
      "changeLog": {
        "createdDateTime": "2024-09-10T14:30:15Z",
        "lastUpdatedDateTime": "2024-09-10T14:30:15Z",
        "createdBy": {
          "href": "/users/system",
          "id": "system",
          "firstName": "System",
          "lastName": "Logger",
          "avatar": {
            "small": "/avatars/system-small.png"
          }
        }
      }
    }
  }
}

Installation​

Prerequisites​

  • A Unizo API key
  • An active Observability integration (Datadog, New Relic)
  • Node.js v20 or higher

MCP Configuration​

Here is an example configuration for setting up the Unizo Observability MCP server:

{
  "mcpServers": {
    "unizo-observability": {
        "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.unizo.ai/mcp/observability",
        "--allow-http",
        "--header",
        "apikey:${UNIZO_API_KEY}"
      ],
      "env": {
        "UNIZO_API_KEY": "your_api_key"
      }
    }
  }
}

Client Setup​

For detailed setup instructions with specific AI clients:

Environment Variables​

The following environment variables are required:

Error Handling​

All tools return errors in a consistent format:

{
  "error": {
    "code": "LOG_SOURCE_NOT_FOUND",
    "message": "Log source 'nginx-error' not found"
  }
}

Common error codes:

  • INTEGRATION_NOT_FOUND: Invalid integration ID
  • LOG_SOURCE_NOT_FOUND: The specified log source was not found
  • METRIC_NOT_AVAILABLE: Metric is missing or invalid
  • TRACE_NOT_FOUND: Trace ID not found in the system
  • RATE_LIMIT_EXCEEDED: API rate limit reached
  • UNAUTHORIZED: Invalid API key or insufficient permissions