Last9 MCP Server enables AI agents to query exception and service graph data from Last9's observability platform. The implementation provides two tools: get_exceptions for retrieving server-side exceptions with details like type, message, and stack trace; and get_service_graph for analyzing upstream and downstream service dependencies with throughput metrics. Built with Go and featuring configurable rate limiting, the server integrates seamlessly with Claude desktop app and Cursor, making it valuable for developers who need AI-assisted troubleshooting and service dependency analysis within their Last9 monitoring environment.
Aún no hay reseñas. ¡Sé el primero en reseñar!
Inicia sesión para unirte a la conversación
Highlight AIRetrieves throughput, error rate, and p95 response time across all services.
Fetches available environments for your services. This should be run first as other APM tools need this information.
Provides a full breakdown of service performance: throughput, error rate, p50/p90/p95/avg/max, apdex, and availability.
Summarizes operations grouped by HTTP endpoints, DB calls, messaging, and HTTP clients.
Generates a dependency map with throughput, latency, and error rates for upstream, downstream, and infrastructure components.
Compares a current window against a baseline to identify regressions, improvements, and outcomes.
Provides server-side exceptions with filters for service and span.
Discovers all databases across your infrastructure, including type, host, throughput, p95 latency, error rate, and dependent services.
Lists the slowest query executions ordered by duration, including trace IDs for deeper investigation.
Analyzes query patterns and aggregates, including execution frequency and average duration.
Retrieves server-side metrics from the database host, such as CPU usage and connection counts.
Executes PromQL range queries over any specified metric.
Performs instant queries using PromQL, allowing for rollup functions like avg_over_time.
Fetches label values for a given series in Prometheus.
Returns all labels available for a specified series in Prometheus.
Executes full JSON pipeline log queries, supporting aggregations, filters, and field extraction.
Retrieves raw log lines for a specified service, with optional filters for severity and content.
Provides a global catalog of attributes in the log schema for a specified time window.
Lists log fields present for an in-progress pipeline, alongside their associated filter fields.
Fetches existing log drop rules.
Creates a new drop rule to reduce log volume at the source.
Executes JSON pipeline trace queries for broad searches and aggregations.
Retrieves traces by exact trace ID or service name for faster lookups.
Provides a global catalog of attributes in the trace schema.
Lists attributes present for an in-progress trace pipeline.
Fetches distinct values for a specific trace attribute.
Tracks deployments, configuration changes, and rollbacks, correlating incidents with changes.
Retrieves alert rule configurations, searchable by various parameters.
Fetches currently firing alerts within a specified time window.
Returns historical firing state for alert rules over a specified time range.
Lists all configured notification channels such as Slack, PagerDuty, and email.
Provides suggestions for potentially misspelled entity names, returning up to 3 closest matches.
Returns all custom dashboards in the organization, including IDs, names, and metadata.
Fetches full definition of a dashboard by its ID, including panels and queries.
Creates a new custom dashboard with defined panels, queries, and metadata.
Updates an existing dashboard by its ID.
Deletes a custom dashboard by its ID.
Lists frozen point-in-time snapshots for a specified dashboard.
Retrieves a full frozen snapshot including panel data for further analysis.
Deletes a frozen snapshot by its ID.
