Loading...
Last9 MCP server provides AI agents with real-time production context (logs, metrics, traces) to assist in code troubleshooting and automated fixes.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
Last9 MCP server provides AI agents with real-time production context (logs, metrics, traces) to assist in code troubleshooting and automated fixes.
The Last9 MCP server is generally safe for read-only operations. The add_drop_rule tool introduces some risk, requiring careful configuration and monitoring. Prometheus queries should be crafted with caution to avoid performance impacts.
Performance depends on the efficiency of the Last9 platform and the complexity of PromQL queries. Avoid overly broad or unoptimized queries.
Cost depends on Last9's pricing model, which may be based on data volume, API calls, or other factors. Consider the cost of storing and processing observability data.
brew install last9-mcp{
"mcpServers": {
"last9": {
"command": "/opt/homebrew/bin/last9-mcp",
"env": {
"LAST9_REFRESH_TOKEN": "<last9_refresh_token>",
"OTEL_EXPORTER_OTLP_ENDPOINT": "<otel_endpoint_url>",
"OTEL_EXPORTER_OTLP_HEADERS": "<otel_headers>"
}
}
}
}get_exceptionsRetrieves server-side exceptions within a specified time range.
Read-only operation, retrieves existing data.
get_service_summaryProvides a summary of a service's performance metrics (throughput, error rate, response time) over a given time range.
Read-only operation, retrieves aggregated data.
get_service_environmentsLists available environments for services.
Read-only operation, retrieves environment names.
get_service_performance_detailsRetrieves detailed performance metrics for a specific service.
Read-only operation, retrieves performance data.
get_service_operations_summaryProvides a summary of operations within a service, such as HTTP endpoints and database queries.
Read-only operation, retrieves operation summaries.
get_service_dependency_graphRetrieves a dependency graph showing incoming and outgoing dependencies for a service.
Read-only operation, retrieves dependency information.
prometheus_range_queryExecutes a PromQL range query to retrieve metrics data over a specified time range.
Read-only operation, retrieves metrics data.
prometheus_instant_queryExecutes a PromQL instant query to retrieve metrics data at a specific point in time.
Read-only operation, retrieves metrics data.
prometheus_label_valuesReturns label values for a given label and PromQL filter query.
Read-only operation, retrieves label values.
prometheus_labelsReturns labels for a given PromQL match query.
Read-only operation, retrieves labels.
get_logsRetrieves logs filtered by service name and/or severity level.
Read-only operation, retrieves log data.
get_drop_rulesRetrieves drop rules for logs, which determine what logs are filtered out.
Read-only operation, retrieves existing drop rules.
add_drop_ruleAdds a new drop rule to filter out specific logs.
Allows modification of log filtering, potentially hiding critical information.
get_service_logsRetrieves raw log entries for a specific service over a time range.
Read-only operation, retrieves log data.
get_log_attributesRetrieves available log attributes (labels) for a specified time window.
Read-only operation, retrieves log attributes.
get_tracesRetrieves traces using JSON pipeline queries for advanced filtering.
Read-only, retrieves trace data.
get_service_tracesRetrieves traces by trace ID or service name with time range filtering.
Read-only, retrieves trace data.
get_trace_attributesRetrieves available trace attributes (series) for a specified time window.
Read-only, retrieves trace attributes.
get_change_eventsRetrieves change events from the last9_change_events Prometheus metric.
Read-only, retrieves change event data.
get_alert_configRetrieves alert configurations (alert rules) from Last9.
Read-only, retrieves alert configurations.
get_alertsRetrieves currently active alerts from the Last9 monitoring system.
Read-only, retrieves active alert data.
API Key
hybrid
The Last9 MCP server is generally safe for read-only operations. The `add_drop_rule` tool introduces some risk, requiring careful configuration and monitoring. Prometheus queries should be crafted with caution to avoid performance impacts.
The agent can read observability data and modify log drop rules. Exercise caution when granting full autonomy due to the potential impact of incorrect drop rule configurations.
Production Tip
Carefully validate any changes to log drop rules in a staging environment before applying them to production to avoid masking critical issues.
API Key authentication is used.
Many tools default to a lookback of 60 minutes, but this can be overridden with specific start and end times.
Use the `get_logs` tool and specify the `severity` parameter (e.g., 'error', 'warn', 'info').
Yes, PromQL supports regular expressions. Refer to the Prometheus documentation for details.
Use the `get_service_environments` tool to retrieve a list of available environments.
The server will return an error message indicating that the query is invalid.
Use specific labels and avoid overly broad queries. Consult Prometheus documentation for query optimization tips.