# usage_stats

查看各模型的使用统计（调用次数、成功率、平均耗时）

Agent View of the PolicyLayer registry record for `usage_stats`. HTML page: https://policylayer.com/tools/7836246-claude-team-mcp/usage-stats

## Facts

- Tool: `usage_stats`
- Server: Claude Team MCP (`7836246/claude-team-mcp`) — https://policylayer.com/tools/7836246-claude-team-mcp.md
- Homepage: https://github.com/7836246/claude-team-mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

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

## Why usage_stats is rated Low

This tool retrieves and displays historical usage metrics about model performance. It does not create, modify, delete, or execute any operations—it only queries and presents data. Therefore it is classified as Read with low severity, as misuse would only expose informational data about model usage patterns without causing any operational harm.

From the tool's own definition: "Tool name 'usage_stats' and description state it 'views usage statistics' (调查各模型的使用统计) including call counts, success rates, and average latency. These are query/retrieval operations with no side effects."

## Use case

AI agents call usage_stats to retrieve information from Claude Team MCP 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 Claude Team MCP:

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

## Other tools on Claude Team MCP (17)

- `fix_bug` — Execute — https://policylayer.com/tools/7836246-claude-team-mcp/fix-bug.md
- `run_workflow` — Execute — https://policylayer.com/tools/7836246-claude-team-mcp/run-workflow.md
- `team_work` — Execute — https://policylayer.com/tools/7836246-claude-team-mcp/team-work.md
- `analyze_project_structure` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/analyze-project-structure.md
- `ask_expert` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/ask-expert.md
- `code_review` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/code-review.md
- `cost_estimate` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/cost-estimate.md
- `explain_plan` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/explain-plan.md
- `history_context` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/history-context.md
- `history_get` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/history-get.md
- `history_list` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/history-list.md
- `history_search` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/history-search.md
- `list_workflows` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/list-workflows.md
- `read_project_files` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/read-project-files.md
- `suggest_workflow` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/suggest-workflow.md
- `team_dashboard` — Read — https://policylayer.com/tools/7836246-claude-team-mcp/team-dashboard.md
- `generate_commit_message` — Write — https://policylayer.com/tools/7836246-claude-team-mcp/generate-commit-message.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=7836246-claude-team-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/7836246-claude-team-mcp