// SCAN REPORT

AIRIOT MCP Server

60 tools. 31 can modify or destroy data without limits.

8 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

31 can modify or destroy data

29 read-only

60 tools total

Community server · catalogue entry verified 30/06/2026

How to control AIRIOT MCP Server ↓

TOOL MAP

What AIRIOT MCP Server exposes to your agents

Read (29) Write / Execute (23) Destructive / Financial (8)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous AIRIOT MCP Server tools

Destructive · High batch_delete_records This tool deletes records in batch, which is an irreversible operation that cannot be undone. Destructive · High delete_file Deleting files cannot be undone and permanently removes data from the system. Destructive · High delete_record This tool permanently removes a single record from a data table without the ability to undo the action. Destructive · High delete_report This tool permanently removes report data from the AIRIOT platform.

31 of AIRIOT MCP Server's 60 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AIRIOT MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and AIRIOT MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "batch_delete_records": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "acknowledge_alarm": {
    "limits": [
      {
        "counter": "acknowledge_alarm_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "batch_confirm_warnings": {
    "limits": [
      {
        "counter": "batch_confirm_warnings_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register AIRIOT MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AIRIOT →

Instant setup, no code required.

FULL CATALOGUE

All 60 AIRIOT MCP Server tools

DESTRUCTIVE 8 tools

Destructive batch_delete_records 批量删除表记录 Destructive delete_file 删除文件 Destructive delete_record 删除单条表记录 Destructive delete_report 删除报表 Destructive delete_table 删除数据表 Destructive delete_warning 删除报警记录 Destructive delete_warning_clean 删除报警清除规则 Destructive delete_warning_rule 删除报警规则

EXECUTE 4 tools

Execute execute_report 执行报表生成，返回报表数据 Execute execute_warning_clean 立即执行清除规则 Execute send_batch_control_commands 批量发送控制命令 Execute send_control_command 向设备发送控制命令

WRITE 19 tools

Write acknowledge_alarm [已废弃] 请使用 update_warning 替代。确认告警，将告警状态从active改为acknowledged Write archive_all_warnings 一键归档所有符合条件的报警 Write create_record 在指定表中创建新记录 Write create_report 创建新报表 Write create_table 创建新的数据表，需要提供完整的表结构定义（schema） Write create_warning 创建新的报警记录 Write create_warning_clean 创建新的报警清除规则 Write create_warning_rule 创建新的报警规则 Write resolve_alarm [已废弃] 请使用 update_warning 替代。解除告警，将告警状态改为resolved Write restore_archived_warning 恢复已归档的报警 Write update_archive_setting 更新自动归档设置 Write update_record 更新表记录数据 Write update_report 更新报表信息 Write update_table 更新数据表信息 Write update_warning 更新报警信息（状态、确认信息等） Write update_warning_clean 更新报警清除规则 Write update_warning_rule 更新报警规则 Write upload_file 上传文件到AIRIOT平台

READ 29 tools

Read batch_confirm_warnings 批量确认报警 Read get_alarm_by_id [已废弃] 请使用 get_warning_by_id 替代。根据ID查询单个告警的详细信息 Read get_alarms [已废弃] 请使用 get_warnings 替代。查询告警列表，支持按级别、状态、时间范围过滤 Read get_archive_setting 获取自动归档设置 Read get_archived_warnings 查询已归档的报警列表 Read get_current_user 获取当前登录用户的信息 Read get_file_info 获取文件信息 Read get_history_data 查询设备属性点的历史时序数据 Read get_latest_data 查询设备属性点的最新数据 Read get_latest_warnings 获取最新的报警列表 Read get_online_stats 统计数据表下设备的在线状态 Read get_record_by_id 根据ID查询单个表记录的详细信息 Read get_record_tags 查询表记录的属性点列表 Read get_report_by_id 根据ID查询单个报表的详细信息 Read get_reports 查询报表列表 Read get_table_by_id 根据ID查询单个数据表的详细信息 Read get_table_records 查询数据表的记录列表，支持过滤、排序、分页和字段投影 Read get_table_tags 查询数据表的所有属性点定义 Read get_tables 查询AIRIOT数据表列表，支持过滤、排序和分页 Read get_users 获取用户列表 Read get_warning_by_id 根据ID查询单个报警的详细信息 Read get_warning_clean_by_id 根据ID查询单个清除规则的详细信息 Read get_warning_cleans 查询报警清除规则列表 Read get_warning_descriptions 获取报警描述列表 Read get_warning_rule_by_id 根据ID查询单个报警规则的详细信息 Read get_warning_rules 查询报警规则列表，支持过滤、排序和分页 Read get_warning_statistics 获取报警统计信息（总数、各级别数量、各状态数量等） Read get_warning_timeline 获取报警时间线数据（指定时间段内的报警趋势） Read get_warnings 查询报警列表，支持按级别、状态、设备、时间范围等过滤

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about AIRIOT MCP Server

Can an AI agent delete data through the AIRIOT MCP Server MCP server? +

Yes. The AIRIOT MCP Server server exposes 8 destructive tools including batch_delete_records, delete_file, delete_record. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through AIRIOT MCP Server? +

The AIRIOT MCP Server server has 19 write tools including acknowledge_alarm, archive_all_warnings, create_record. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach AIRIOT MCP Server.

How many tools does the AIRIOT MCP Server MCP server expose? +

60 tools across 4 categories: Destructive, Execute, Read, Write. 29 are read-only. 31 can modify, create, or delete data.

How do I enforce a policy on AIRIOT MCP Server? +

Register the AIRIOT MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every AIRIOT MCP Server tool call.

Deterministic rules across all 60 AIRIOT MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AIRIOT →

Instant setup, no code required.

60 AIRIOT MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.