8 tools from the Logclaw MCP Server, categorised by risk level.
View the Logclaw policy →logclaw_get_anomalies Get recent anomaly detections. Anomalies are auto-detected using Z-score analysis on error rates. Returns score, detection mode, service. logclaw_get_incident Get full incident details including root cause, causal chain, evidence logs, traces, timeline, blast radius, and suggested fix. 2/5 logclaw_list_incidents List and filter LogClaw incidents. Returns summaries with ID, title, severity, state, service, timestamps. logclaw_search_logs Search raw logs in LogClaw. Filter by service, level, time range, and query. Returns entries with timestamp, service, level, message, trace_id. 2/5 logclaw_service_health Check the health status of LogClaw pipeline services (ticketing agent, etc). Returns status and latency. logclaw_bulk_update Update multiple incidents at once. Acknowledge, investigate, mitigate, or resolve several incidents in a single call. 2/5 logclaw_export_incidents Export incidents in CSV, markdown table, or JSON format for easy copy-paste or sharing. 2/5 logclaw_update_incident Transition an incident state (acknowledge, investigate, mitigate, resolve) or add a timeline note. 2/5 The Logclaw MCP server exposes 8 tools across 2 categories: Read, Write.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Logclaw server.
Logclaw tools are categorised as Read (5), Write (3). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept