# paper_health

检查论文下载服务各数据源的可用性（Unpaywall、arXiv、Sci-Hub 镜像）。

Agent View of the PolicyLayer registry record for `paper_health`. HTML page: https://policylayer.com/tools/45645678a-scholar-mcp/paper-health

## Facts

- Tool: `paper_health`
- Server: Scholar MCP Server (`45645678a/scholar-mcp`) — https://policylayer.com/tools/45645678a-scholar-mcp.md
- Homepage: https://github.com/45645678a/scholar-mcp
- Risk category: Read (Low risk)
- Registry record: grade A, 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": "paper_health",
    "arguments": {}
  }
}
```

## Why paper_health is rated Low

This is a diagnostic/monitoring tool that queries the operational status of external academic data sources. It performs a read-only health check operation with no side effects, no data retrieval for the user, no modifications, and no external state changes beyond a simple availability probe. Low severity because even misuse cannot harm data or systems—it can only report status information.

From the tool's own definition: "Tool description states it 'checks the availability' (检查可用性) of paper download data sources (Unpaywall, arXiv, Sci-Hub mirrors). The verb 'check' and 'availability' indicate status monitoring or health checking operations without modifying any data."

## Use case

AI agents call paper_health to retrieve information from Scholar MCP Server 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 Scholar MCP Server:

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

## Other tools on Scholar MCP Server (7)

- `paper_ai_analyze` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-ai-analyze.md
- `paper_citation_graph` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-citation-graph.md
- `paper_download` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-download.md
- `paper_recommend` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-recommend.md
- `paper_search` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-search.md
- `paper_translate` — Read — https://policylayer.com/tools/45645678a-scholar-mcp/paper-translate.md
- `paper_batch_download` — Write — https://policylayer.com/tools/45645678a-scholar-mcp/paper-batch-download.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=45645678a-scholar-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/45645678a-scholar-mcp