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
Throughput, error rate, p95 response time across all services.
Available environments for your services. Run this first — other APM tools need `env` from here.
Full breakdown: throughput, error rate, p50/p90/p95/avg/max, apdex, availability.
Operations grouped by HTTP endpoints, DB calls, messaging, HTTP clients.
Dependency map with throughput, latency, and error rates for upstream/downstream/infra.
Server-side exceptions with service and span filters.
Discover all databases across your infrastructure: DB type, host, throughput (queries/min), p95 latency, error rate, number of dependent services.
The actual slowest query executions, ordered by duration, with trace IDs for drilling into full traces.
Query patterns and aggregates: how often a query runs, average/p95 duration, error rate.
Server-side metrics from the DB host itself (CPU, connections, buffer hit rates — depends on your DB system).
PromQL range queries over any metric.
Instant queries; use rollup functions like `avg_over_time`, `sum_over_time`.
Label values for a given series.
All labels available for a series.
Full JSON pipeline log queries (aggregations, filters, field extraction).
Raw log lines for a service, filterable by severity and body content.
Available attributes in the log schema for a time window.
Log drop rules from Last9 Control Plane.
Create a new drop rule to cut log volume at the source.
JSON pipeline trace queries for broad searches and aggregations.
Traces by exact trace ID or service name. Use this when you have a trace ID — it's faster.
Available attributes in the trace schema.
Deployments, config changes, rollbacks. Correlate incidents with what changed.
Alert rule configurations — searchable by name, severity, type, tags.
Currently firing alerts within a time window.
Historical firing state per alert rule over a time range, grouped by `rule_id`.
Configured notification channels (Slack, PagerDuty, email, etc.).
All custom dashboards in your org: IDs, names, and metadata.
Full dashboard definition by ID, including panels and queries.
Create a new custom dashboard with panels, queries, and metadata.
Update an existing dashboard by ID.
Delete a custom dashboard by ID.
When the agent isn't sure about an entity name, this returns the closest matches from your catalog.
