// SCAN REPORT

Aos

37 tools. 23 can modify or destroy data without limits.

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

Last updated: 12 Oct 2026

23 can modify or destroy data

14 read-only

37 tools total

Community server · catalogue entry checked 12/10/2026 · full schemas captured for 35 of 37 tools

How to control Aos ↓

TOOL MAP

What Aos exposes to your agents

Read (14) Write / Execute (21) Destructive / Financial (2)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Aos costs in tokens

3,681 tokens of tool definitions, loaded on every request

1.8% of a 200k context window

198 heaviest tool: update_strategy

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Aos tools

Destructive · High delete_backlog_item The 'delete' verb paired with a business artifact (backlog_item) indicates this tool permanently removes data without the ability to undo or recover it. Destructive · High delete_kpi_entry The name unambiguously signals irreversible deletion of data. Write · Medium complete_task The tool modifies task state by marking a task as complete, which is a write operation. Write · Medium complete_todo Completing a to-do is a reversible modification operation (can typically be undone by reverting status), so it fits Write rather than Destructive or Execute.

23 of Aos's 37 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Aos

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

Deny destructive operations

{
  "delete_backlog_item": {
    "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

{
  "complete_task": {
    "limits": [
      {
        "counter": "complete_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_activity_logs": {
    "limits": [
      {
        "counter": "get_activity_logs_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 Aos — 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 AOS →

Instant setup, no code required.

FULL CATALOGUE

All 37 Aos tools

DESTRUCTIVE 2 tools

Destructive delete_backlog_item delete_backlog_item Destructive delete_kpi_entry delete_kpi_entry

READ 14 tools

Read get_activity_logs get_activity_logs Read get_backlog get_backlog Read get_briefing get_briefing Read get_issues get_issues Read get_kpi get_kpi Read get_members get_members Read get_missions get_missions Read get_org_chart get_org_chart Read get_seat get_seat Read get_strategy get_strategy Read get_tasks get_tasks Read get_todos get_todos Read list_teams list_teams Read whoami whoami

EXPLORE

Related servers

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

FAQ

Questions about Aos

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

Yes. The Aos server exposes 2 destructive tools including delete_backlog_item, delete_kpi_entry. 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 Aos? +

The Aos server has 21 write tools including complete_task, complete_todo, create_backlog_item. 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 Aos.

How many tools does the Aos MCP server expose? +

37 tools across 3 categories: Destructive, Read, Write. 14 are read-only. 23 can modify, create, or delete data.

How do I enforce a policy on Aos? +

Register the Aos 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 Aos tool call.

Deterministic rules across all 37 Aos tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AOS →

Instant setup, no code required.

37 Aos tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Aos's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →