# get_kpi

A read tool on the Aos MCP server.

Agent View of the PolicyLayer registry record for `get_kpi`. HTML page: https://policylayer.com/tools/funny-booth-aos-mcp-server/get-kpi

## Facts

- Tool: `get_kpi`
- Server: Aos (`@funny-booth/aos-mcp-server`) — https://policylayer.com/tools/funny-booth-aos-mcp-server.md
- Install: `npx -y @funny-booth/aos-mcp-server`
- Homepage: https://www.npmjs.com/package/@funny-booth/aos-mcp-server
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `team_id` | string | no | 対象チームID（省略時はユーザーの既定チーム） |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_kpi",
    "arguments": {}
  }
}
```

## Why get_kpi is rated Low

The 'get_' prefix is strongly associated with read operations that fetch existing data without side effects. Given the context of metric management and lack of any indication of write/execute/destructive capabilities in the name, this is classified as a Read operation with low severity since it only retrieves metrics data.

From the tool's own definition: "Tool name 'get_kpi' indicates retrieval of key performance indicator data with no modification capability. Description is empty, but sibling tools show this server manages tasks, issues, and metrics, suggesting 'get_kpi' retrieves KPI metric data."

## Use case

AI agents call get_kpi to retrieve information from Aos without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Aos:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_kpi": {}
  }
}
```

## Other tools on Aos (36)

- `delete_backlog_item` — Destructive — https://policylayer.com/tools/funny-booth-aos-mcp-server/delete-backlog-item.md
- `delete_kpi_entry` — Destructive — https://policylayer.com/tools/funny-booth-aos-mcp-server/delete-kpi-entry.md
- `get_activity_logs` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-activity-logs.md
- `get_backlog` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-backlog.md
- `get_briefing` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-briefing.md
- `get_issues` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-issues.md
- `get_members` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-members.md
- `get_missions` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-missions.md
- `get_org_chart` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-org-chart.md
- `get_seat` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-seat.md
- `get_strategy` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-strategy.md
- `get_tasks` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-tasks.md
- `get_todos` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/get-todos.md
- `list_teams` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/list-teams.md
- `whoami` — Read — https://policylayer.com/tools/funny-booth-aos-mcp-server/whoami.md
- `complete_task` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/complete-task.md
- `complete_todo` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/complete-todo.md
- `create_backlog_item` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-backlog-item.md
- `create_issue` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-issue.md
- `create_kpi_metric` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-kpi-metric.md
- `create_member` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-member.md
- `create_mission` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-mission.md
- `create_task` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-task.md
- `create_team` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-team.md
- `create_todo` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/create-todo.md
- `invite_to_team` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/invite-to-team.md
- `log_activity` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/log-activity.md
- `reject_task` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/reject-task.md
- `update_backlog_item` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/update-backlog-item.md
- `update_issue` — Write — https://policylayer.com/tools/funny-booth-aos-mcp-server/update-issue.md
- …and 6 more: https://policylayer.com/tools/funny-booth-aos-mcp-server.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=funny-booth-aos-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/funny-booth-aos-mcp-server