# query_loki_logs Executes a LogQL query against a Loki datasource to retrieve log entries or metric values Agent View of the PolicyLayer registry record for `query_loki_logs`. HTML page: https://policylayer.com/tools/0xteamhq-mcp-grafana/query-loki-logs ## Facts - Tool: `query_loki_logs` - Server: Grafana MCP Server (`0xteamhq/mcp-grafana`) — https://policylayer.com/tools/0xteamhq-mcp-grafana.md - Homepage: https://github.com/0xteamhq/mcp-grafana - Risk category: Execute (High risk) - Registry record: grade C, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "query_loki_logs", "arguments": {} } } ``` ## Why query_loki_logs is rated High The tool explicitly 'executes' a query (LogQL) against an external datasource. While the primary outcome is reading log data, the action involves running a query against an external system, placing it in the Execute category. The blast radius is medium — a misused query could expose sensitive log data or overload the Loki datasource, but it cannot modify or delete data. From the tool's own definition: "'Executes a LogQL query against a Loki datasource to retrieve log entries or metric values'" ## Use case AI agents invoke query_loki_logs to trigger actions in Grafana MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Grafana MCP Server: ```json { "version": "1", "default": "deny", "tools": { "query_loki_logs": { "limits": [ { "counter": "query_loki_logs_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Grafana MCP Server (42) - `fetch_pyroscope_profile` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/fetch-pyroscope-profile.md - `find_error_pattern_logs` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/find-error-pattern-logs.md - `find_slow_requests` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/find-slow-requests.md - `generate_deeplink` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/generate-deeplink.md - `get_alert_rule_by_uid` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-alert-rule-by-uid.md - `get_assertions` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-assertions.md - `get_current_oncall_users` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-current-oncall-users.md - `get_dashboard_by_uid` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-dashboard-by-uid.md - `get_dashboard_panel_queries` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-dashboard-panel-queries.md - `get_dashboard_property` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-dashboard-property.md - `get_dashboard_summary` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-dashboard-summary.md - `get_datasource_by_name` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-datasource-by-name.md - `get_datasource_by_uid` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-datasource-by-uid.md - `get_incident` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-incident.md - `get_oncall_shift` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-oncall-shift.md - `get_sift_analysis` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-sift-analysis.md - `get_sift_investigation` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/get-sift-investigation.md - `list_alert_rules` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-alert-rules.md - `list_contact_points` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-contact-points.md - `list_datasources` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-datasources.md - `list_incidents` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-incidents.md - `list_loki_label_names` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-loki-label-names.md - `list_loki_label_values` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-loki-label-values.md - `list_oncall_schedules` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-oncall-schedules.md - `list_oncall_teams` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-oncall-teams.md - `list_oncall_users` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-oncall-users.md - `list_prometheus_label_names` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-prometheus-label-names.md - `list_prometheus_label_values` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-prometheus-label-values.md - `list_prometheus_metric_metadata` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-prometheus-metric-metadata.md - `list_prometheus_metric_names` — Read — https://policylayer.com/tools/0xteamhq-mcp-grafana/list-prometheus-metric-names.md - …and 12 more: https://policylayer.com/tools/0xteamhq-mcp-grafana.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0xteamhq-mcp-grafana · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xteamhq-mcp-grafana