last9/last9-mcp-server
Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster
Ads
Overview
Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster
Installation
claude mcp add --transport http last9 https://app.last9.io/api/v4/organizations/<org_slug>/mcp
Configuration
{
"mcpServers": {
"last9": {
"type": "http",
"url": "https://app.last9.io/api/v4/organizations/<org_slug>/mcp"
}
}Capabilities
- Service health overview
Ask for a ranked fleet summary with `get_service_summary` to see request counts, throughput, and HTTP/gRPC error rates across services and environments.
- Database performance analysis
Use `get_database_slow_queries` to identify the slowest query executions with trace IDs, or `get_databases` to discover all databases and their throughput metrics.
- Log investigation
Query `get_service_logs` for raw log lines filtered by severity and body content, or use `get_logs` for complex JSON pipeline queries with aggregations.
- Trace debugging
Retrieve `get_service_traces` by trace ID for fast lookup, or use `get_trace_waterfall` to visualize a single trace's parent-child span hierarchy with timing details.
- Prometheus metrics exploration
Run `prometheus_range_query` for PromQL range queries over any metric, or use `prometheus_label_values` to discover available label values for a series.
- Alert and change correlation
Check `get_alerts` for currently firing alerts, `get_change_events` for deployments and config changes, and `get_alert_config` to search alert rule configurations.
Tags
- observability-incident
- monitoring
- devops-infrastructure
- debugging
- log-management
- awesome-list
Related MCP servers
ingero-io/ingero
eBPF-based GPU causal observability agent with MCP server. Traces CUDA Runtime/Driver APIs and host kernel events to build causal chains explaining GPU latency.
adanb13/cirdan
AI infrastructure cartographer & MCP server: fingerprints, graphs, and watches the live infrastructure an agent can reach (Docker, Kubernetes, cloud, IaC) and detects incidents.
agentkitai/agentlens
Tamper-evident observability for AI agents: a SHA-256 hash-chained audit log with chain verification and signed export (EU AI Act Art. 12). Instrument any agent with zero code via `npx -y @agentlensai/mcp`; also ingests OpenTelemetry GenAI traces.
alilxxey/openobserve-community-mcp
Read-only MCP server for OpenObserve Community Edition via REST API. Search logs, traces, stream schemas, and dashboards without requiring the Enterprise license.