获取 CLS 告警执行详情日志。查询指定时间范围内的告警策略执行详情，使用方式类似 SearchLog，通过 Query 参数传入检索分析语句。 常用查询语句（直接作为 Query 参数传入）： 1. 查询执行详情列表（最常用）： NOT condition_evaluate_result:"Skip" AND condition_evaluate_result:[* TO *] | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, topic_type, trigger, conditi...
Risk signalsAccepts freeform code/query input (Query)
Part of the Cls server.
Free to start. No card required.
AI agents call GetAlarmLog to retrieve information from Cls without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though GetAlarmLog only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"GetAlarmLog": {}
}
}See the full Cls policy for all 19 tools.
These attack patterns abuse exactly the kind of access GetAlarmLog gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
获取 CLS 告警执行详情日志。查询指定时间范围内的告警策略执行详情，使用方式类似 SearchLog，通过 Query 参数传入检索分析语句。 常用查询语句（直接作为 Query 参数传入）： 1. 查询执行详情列表（最常用）： NOT condition_evaluate_result:"Skip" AND condition_evaluate_result:[* TO *] | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, topic_type, trigger, condition_evaluate_result, notification_send_result, notify_type, silent, record_id, record_group_id, summary_cn ORDER BY timestamp DESC LIMIT 1000 2. 按告警策略过滤执行详情： alert_id:"alarm-xxxx" AND NOT condition_evaluate_result:"Skip" AND condition_evaluate_result:[* TO *] | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, trigger, condition_evaluate_result, notification_send_result, notify_type, silent, summary_cn ORDER BY timestamp DESC LIMIT 1000 3. 按监控对象过滤执行详情： monitored_object:"topic-id-xxxx" AND NOT condition_evaluate_result:"Skip" AND condition_evaluate_result:[* TO *] | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, trigger, condition_evaluate_result, notification_send_result, notify_type, silent, summary_cn ORDER BY timestamp DESC LIMIT 1000 4. 查询执行失败的记录： condition_evaluate_result:"ProcessError" | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, trigger, condition_evaluate_result, summary_cn ORDER BY timestamp DESC LIMIT 1000 5. 查询通知失败的记录： (notification_send_result:"SendFail" OR notification_send_result:"SendPartFail") | SELECT __TIMESTAMP__ as timestamp, alert_id, alert_name, monitored_object, notification_send_result, summary_cn ORDER BY timestamp DESC LIMIT 1000 6. 统计各告警策略执行次数 Top 50： NOT condition_evaluate_result:"Skip" AND condition_evaluate_result:[* TO *] | SELECT alert_id, alert_name, count(*) AS total, count_if(condition_evaluate_result='ProcessError') AS failure_count, count_if(notification_send_result!='NotSend') AS notify_total, count_if(notification_send_result='SendFail' OR notification_send_result='SendPartFail') AS notify_failure_count GROUP BY alert_id, alert_name ORDER BY total DESC LIMIT 50 常用过滤字段及枚举值： - alert_id: 告警策略ID - monitored_object: 监控对象（日志主题ID） - condition_evaluate_result: QueryResultMatch(满足) / QueryResultUnmatch(不满足) / ProcessError(执行失败) / Skip(跳过) - notification_send_result: SendSuccess(成功) / SendFail(失败) / SendPartFail(部分失败) / NotSend(未发送) 分页说明：首次不传 Context；若返回 ListOver 为 false，用返回的 Context 获取后续数据。Context 有效期 1 小时，翻页时请勿修改其他参数，总计最多获取 1 万条。SQL 分析结果的分页请使用 LIMIT/OFFSET。 返回信息：SQL 分析时返回 AnalysisRecords；非 SQL 查询时返回 Results 列表（每条含 Time、LogJson）、Context（分页标识）、ListOver（是否查询完毕）。. It is categorised as a Read tool in the Cls MCP Server, which means it retrieves data without modifying state.
Register the Cls MCP server in PolicyLayer and add a rule for GetAlarmLog: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cls. Nothing to install.
GetAlarmLog is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the GetAlarmLog rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for GetAlarmLog. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
GetAlarmLog is provided by the Cls MCP server (cls-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Cls tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.