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.
暂无评论. 成为第一个评论的人!
登录以参与讨论
Recommended first call when a request names no service or tool. Returns environments, signals seen in the last hour, service and alert-group counts, firing alerts, and the current time.
Returns the current time, plus absolute bounds for common timeframes (last 2h, yesterday, etc.) in any IANA zone or common abbreviation.
Ranked fleet rows providing interval request count, throughput, HTTP error counts, and gRPC error counts.
Returns available environments for your services.
Provides a full performance breakdown including throughput, error rate, and various percentiles.
Operations grouped by HTTP endpoints, DB calls, and messaging.
Returns a dependency map with throughput, latency, and error rates.
Compares a current window against a baseline to identify regressions or improvements.
Fetches server-side exceptions with service and span filters.
Discovers all databases across your infrastructure, including metrics like throughput and error rate.
Returns the slowest query executions ordered by duration.
Provides query patterns and aggregates such as average duration and error rate.
Fetches server-side metrics from the database host.
Executes PromQL range queries over any metric.
Executes instant queries using rollup functions.
Returns label values for a given series.
Returns all labels available for a series.
Performs full JSON pipeline log queries with aggregations and filters.
Fetches log lines for a specific service, filterable by severity and content.
Clusters a service's log lines into message templates for analysis.
Identifies log templates that have changed against a baseline.
Returns a global catalog of attributes in the log schema for a time window.
Executes JSON pipeline trace queries for broad searches and aggregations.
Fetches traces by exact trace ID or service name.
Returns deployments, config changes, and rollbacks.
Analyzes whether a change has caused any issues, comparing service metrics before and after the change.
Returns configured alert groups with metadata.
Summarizes on-call health over a specified window.
Identifies uncovered signals and alert groups.
Fetches alert rule configurations by various filters.
Returns currently firing alerts within a specified time window.
Creates a new alert rule in an existing alert group, always created as disabled.
Permanently deletes an alert rule.
Creates a new notification channel for alerts.
Routes an existing channel to an alert group.
Removes an attachment of a notification channel from an alert group.
Permanently deletes a notification channel that has no attachments.
Provides suggestions for entity names when a query is uncertain.
Returns the telemetry profile for a specified service.
Returns all custom dashboards in the organization.
Fetches the full dashboard definition by ID, including its panels and queries.
Creates a new custom dashboard.
Updates an existing dashboard by ID.
Makes targeted edits to an existing dashboard by ID.
Deletes a custom dashboard by ID.
Returns services that have profiling data in the specified time window.
Returns a nested flamegraph tree for a specified service.
Returns a ranking of the hottest functions for a specified service.
Returns a short natural-language triage of the profile for one service.